sglang 0.5.3__tar.gz → 0.5.3.post1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {sglang-0.5.3/sglang.egg-info → sglang-0.5.3.post1}/PKG-INFO +4 -4
- {sglang-0.5.3 → sglang-0.5.3.post1}/pyproject.toml +4 -4
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/bench_one_batch.py +0 -2
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/bench_serving.py +224 -127
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/compile_deep_gemm.py +3 -0
- sglang-0.5.3.post1/sglang/launch_server.py +16 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/__init__.py +2 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/falcon_h1.py +12 -58
- sglang-0.5.3.post1/sglang/srt/configs/mamba_utils.py +117 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/model_config.py +68 -31
- sglang-0.5.3.post1/sglang/srt/configs/nemotron_h.py +286 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/qwen3_next.py +11 -43
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/decode.py +7 -18
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/decode_kvcache_offload_manager.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/nixl/conn.py +55 -23
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/prefill.py +17 -32
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/engine.py +2 -2
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/grpc_request_manager.py +10 -23
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/grpc_server.py +220 -80
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/http_server.py +49 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/protocol.py +159 -31
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_chat.py +13 -71
- sglang-0.5.3.post1/sglang/srt/entrypoints/openai/serving_tokenize.py +144 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/environ.py +4 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/function_call_parser.py +8 -6
- sglang-0.5.3.post1/sglang/srt/grpc/sglang_scheduler_pb2.py +119 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/grpc/sglang_scheduler_pb2.pyi +64 -6
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/grpc/sglang_scheduler_pb2_grpc.py +88 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/attention_registry.py +31 -22
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/layernorm_gated.py +47 -30
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/flashattention_backend.py +0 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/flashinfer_backend.py +223 -6
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/flashinfer_mla_backend.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/hybrid_linear_attn_backend.py +165 -59
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/causal_conv1d.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/causal_conv1d_triton.py +9 -4
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/mamba.py +189 -241
- sglang-0.5.3.post1/sglang/srt/layers/attention/mamba/mamba2_metadata.py +211 -0
- sglang-0.5.3.post1/sglang/srt/layers/attention/mamba/mixer2_rms_norm_gated.py +120 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_bmm.py +0 -50
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_chunk_scan.py +0 -60
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_chunk_state.py +0 -111
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_state_passing.py +0 -11
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_backend.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/logits_processor.py +136 -6
- sglang-0.5.3.post1/sglang/srt/layers/modelopt_utils.py +11 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/cutlass_w4a8_moe.py +18 -21
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/ep_moe/kernels.py +31 -452
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/ep_moe/layer.py +8 -286
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/layer.py +6 -11
- sglang-0.5.3.post1/sglang/srt/layers/moe/moe_runner/deep_gemm.py +304 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/moe_runner/runner.py +3 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/utils.py +7 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/__init__.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/fp8.py +84 -18
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/modelopt_quant.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/quark.py +3 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/w4afp8.py +2 -16
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/lora_manager.py +0 -8
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/overlap_utils.py +18 -16
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/schedule_batch.py +119 -90
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/schedule_policy.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler.py +213 -126
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_metrics_mixin.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_output_processor_mixin.py +180 -86
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/tokenizer_manager.py +270 -53
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/tp_worker.py +39 -28
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/allocator.py +7 -2
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/chunk_cache.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/memory_pool.py +162 -68
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/radix_cache.py +8 -3
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/swa_radix_cache.py +70 -14
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/cuda_graph_runner.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/forward_batch_info.py +4 -18
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/model_runner.py +55 -51
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/__init__.py +1 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/loader.py +187 -6
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/weight_utils.py +3 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/falcon_h1.py +11 -9
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3_mm.py +16 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/grok.py +5 -13
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mixtral.py +1 -3
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mllama4.py +11 -1
- sglang-0.5.3.post1/sglang/srt/models/nemotron_h.py +514 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/utils.py +5 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/sampling_batch_info.py +11 -9
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/server_args.py +100 -33
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/eagle_worker.py +11 -13
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/ngram_worker.py +12 -11
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/spec_utils.py +0 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/two_batch_overlap.py +1 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/common.py +18 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/hf_transformers_utils.py +2 -0
- sglang-0.5.3.post1/sglang/test/longbench_v2/__init__.py +1 -0
- sglang-0.5.3.post1/sglang/test/longbench_v2/test_longbench_v2_eval.py +238 -0
- sglang-0.5.3.post1/sglang/test/longbench_v2/validate_longbench_v2.py +337 -0
- sglang-0.5.3.post1/sglang/test/longbench_v2/validate_longbench_v2_standalone.py +306 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/run_eval.py +40 -0
- sglang-0.5.3.post1/sglang/test/simple_eval_longbench_v2.py +332 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_cutlass_w4a8_moe.py +9 -19
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_deterministic.py +18 -2
- sglang-0.5.3.post1/sglang/test/test_deterministic_utils.py +81 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_disaggregation_utils.py +63 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_utils.py +32 -11
- sglang-0.5.3.post1/sglang/version.py +1 -0
- {sglang-0.5.3 → sglang-0.5.3.post1/sglang.egg-info}/PKG-INFO +4 -4
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang.egg-info/SOURCES.txt +16 -5
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang.egg-info/requires.txt +3 -3
- sglang-0.5.3/sglang/launch_server.py +0 -30
- sglang-0.5.3/sglang/srt/grpc/sglang_scheduler_pb2.py +0 -111
- sglang-0.5.3/sglang/srt/layers/attention/mamba/mamba_utils.py +0 -81
- sglang-0.5.3/sglang/srt/managers/tp_worker_overlap_thread.py +0 -311
- sglang-0.5.3/sglang/test/test_block_fp8_ep.py +0 -358
- sglang-0.5.3/sglang/version.py +0 -1
- {sglang-0.5.3 → sglang-0.5.3.post1}/LICENSE +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/README.md +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/setup.cfg +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/bench_offline_throughput.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/bench_one_batch_server.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/check_env.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/eval/llama3_eval.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/eval/loogle_eval.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/global_config.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/api.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/anthropic.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/base_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/litellm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/openai.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/runtime_endpoint.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/vertexai.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/chat_template.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/choices.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/compiler.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/interpreter.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/ir.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/tracer.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/profiler.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/_custom_ops.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/aio_rwlock.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/batch_invariant_ops/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/batch_invariant_ops/batch_invariant_ops.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/bench_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/chatglm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/dbrx.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/deepseekvl2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/device_config.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/dots_ocr.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/dots_vlm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/exaone.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/internvl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/janus_pro.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/kimi_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/kimi_vl_moonvit.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/load_config.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/longcat_flash.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/qwen3_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/step3_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/update_config.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/base_connector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/redis.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/remote_instance.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/s3.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/serde/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/serde/safe_serde.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/serde/serde.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constants.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/base_grammar_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/llguidance_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/outlines_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/outlines_jump_forward.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/reasoner_grammar_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/triton_ops/bitmask_ops.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/xgrammar_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/custom_op.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/dump_comparator.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/dump_loader.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/dumper.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/text_comparator.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/ascend/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/ascend/conn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/ascend/transfer_engine.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/base/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/base/conn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/common/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/common/conn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/common/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/decode_schedule_batch_mixin.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/fake/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/fake/conn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/kv_events.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/mini_lb.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/mooncake/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/mooncake/conn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/mooncake/transfer_engine.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/nixl/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/communication_op.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/all_reduce_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/cuda_wrapper.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/custom_all_reduce.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/hpu_communicator.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/npu_communicator.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/pymscclpp.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/pynccl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/pynccl_allocator.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/pynccl_wrapper.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/quick_all_reduce.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/shm_broadcast.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/symm_mem.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/xpu_communicator.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/naive_distributed.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/parallel_state.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/EngineBase.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/context.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/harmony_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/http_server_engine.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_base.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_completions.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_embedding.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_rerank.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_responses.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_score.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/tool_server.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/usage_processor.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/tool.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_algorithms/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_algorithms/deepseek.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_algorithms/deepseek_vec.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_manager.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_simulator/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_simulator/reader.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/expert_distribution.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/expert_location.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/expert_location_dispatch.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/expert_location_updater.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/base_format_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/core_types.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/deepseekv31_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/deepseekv3_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/ebnf_composer.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/glm4_moe_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/gpt_oss_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/json_array_parser.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/kimik2_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/llama32_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/mistral_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/pythonic_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/qwen25_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/qwen3_coder_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/step3_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/grpc/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/grpc/compile_proto.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/host_shared_memory.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/activation.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/amx_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/aiter_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/ascend_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/base_attn_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/cutlass_mla_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/double_sparsity_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/dual_chunk_flashattention_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/chunk.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/chunk_delta_h.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/chunk_o.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/chunk_scaled_dot_kkt.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/cumsum.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/fused_recurrent.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/fused_sigmoid_gating_recurrent.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/index.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/l2norm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/op.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/solve_tril.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/wy_fast.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/flashmla_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/hybrid_attn_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/intel_amx_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/layernorm_gated.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/mamba_ssm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_combined.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/merge_state.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/npu_ops/mla_preprocess.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/dequant_k_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/index_buf_accessor.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/nsa_indexer.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/quant_k_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/tilelang_kernel.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/transform_index.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/tbo_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/torch_flex_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/torch_native_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/decode_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/extend_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/merge_state.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/prefill_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/trtllm_mha_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/trtllm_mla_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/vision.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/vision_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/wave_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/wave_ops/decode_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/wave_ops/extend_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/wave_ops/prefill_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/communicator.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/dp_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/elementwise.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/flashinfer_comm_fusion.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/layernorm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/linear.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/model_parallel.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/cutlass_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/cutlass_moe_params.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/ep_moe/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/flashinfer_cutedsl_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_native.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1024,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Instinct_MI300X.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Instinct_MI325X.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Radeon_Graphics.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Instinct_MI300X.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Instinct_MI325X.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Radeon_Graphics.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Instinct_MI300X.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Instinct_MI325X.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Radeon_Graphics.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_L40S.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Instinct_MI300X.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Instinct_MI325X.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Radeon_Graphics.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H20.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H20.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H20.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=96,device_name=NVIDIA_H20.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=129,N=352,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=160,N=320,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=161,N=192,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_0/E=16,N=1024,device_name=NVIDIA_B200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=352,device_name=NVIDIA_RTX_6000_Ada_Generation,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=768,device_name=NVIDIA_H20.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=320,device_name=NVIDIA_H20-3e.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=352,device_name=NVIDIA_RTX_5880_Ada_Generation,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=161,N=384,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_H800,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=512,device_name=NVIDIA_H20.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=64,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H20-3e.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H800,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_B200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_H20-3e.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H200.json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/moe_runner/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/moe_runner/base.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/moe_runner/triton.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/rocm_moe_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/router.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/token_dispatcher/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/token_dispatcher/base.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/token_dispatcher/deepep.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/token_dispatcher/standard.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/topk.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/multimodal.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/parameter.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/pooler.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/awq.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/awq_triton.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/base_config.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/blockwise_int8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/fp8_kernel.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/fp8_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/fpgemm_fp8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/gptq.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/int8_kernel.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/int8_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/kv_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/marlin_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/marlin_utils_fp8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/moe_wna16.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/mxfp4.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/mxfp4_tensor.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/petit.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/petit_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/qoq.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/quark_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/schemes/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/schemes/quark_scheme.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/rocm_mxfp4_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/unquant.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/w8a8_fp8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/w8a8_int8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/radix_attention.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/rocm_linear_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/rotary_embedding.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/sampler.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/torchao_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/vocab_parallel_embedding.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/backend/base_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/backend/chunked_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/backend/triton_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/layers.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/lora.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/lora_config.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/lora_registry.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/mem_pool.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/chunked_sgmv_expand.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/chunked_sgmv_shrink.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/gate_up_lora_b.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/qkv_lora_b.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/sgemm_lora_a.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/sgemm_lora_b.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/async_dynamic_batch_tokenizer.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/cache_controller.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/configure_logging.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/data_parallel_controller.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/detokenizer_manager.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/disagg_service.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/io_struct.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/mm_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/multi_tokenizer_mixin.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/multimodal_processor.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_input_blocker.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_profiler_mixin.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_recv_skipper.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_update_weights_mixin.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/session_controller.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/template_manager.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/tokenizer_communicator_mixin.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/allocator_ascend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/base_prefix_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/evict_policy.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/flush_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/hicache_storage.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/hiradix_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/memory_pool_host.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/multimodal_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/radix_cache_cpp.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/aibrix_kvcache/aibrix_kvcache_storage.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/aibrix_kvcache/unit_test.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/backend_factory.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/eic/eic_storage.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/eic/test_unit.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/hf3fs_client.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/hf3fs_usrbio_client.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/lmcache/lmc_radix_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/lmcache/unit_test.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/mooncake_store/test_mooncake_store.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/nixl/hicache_nixl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/nixl/nixl_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/metrics/collector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/metrics/func_timer.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/metrics/startup_func_log_and_timer.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/metrics/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/cpu_graph_runner.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/npu_graph_runner.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/remote_instance_weight_loader_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/apertus.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/arcee.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/baichuan.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/bailing_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/bailing_moe_nextn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/bert.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/chatglm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/clip.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/commandr.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/dbrx.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek_janus_pro.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek_nextn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek_v2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek_vl2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/dots_ocr.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/dots_vlm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/dots_vlm_vit.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/ernie4.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/ernie4_eagle.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/exaone.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma2_reward.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3_causal.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3n_audio.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3n_causal.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3n_mm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4_moe_nextn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4v.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4v_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gpt2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gpt_bigcode.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gpt_oss.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/granite.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/granitemoe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/hunyuan.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/idefics2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/internlm2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/internlm2_reward.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/interns1.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/internvl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/kimi_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/kimi_vl_moonvit.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama4.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_classification.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_eagle.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_eagle3.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_embedding.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_reward.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llava.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llavavid.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/longcat_flash.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/longcat_flash_nextn.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mimo.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mimo_mtp.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/minicpm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/minicpm3.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/minicpmo.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/minicpmv.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mistral.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mixtral_quant.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mllama.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/nemotron_nas.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/olmo.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/olmo2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/olmoe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/opt.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/persimmon.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi3_small.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi4mm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi4mm_audio.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi4mm_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phimoe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/pixtral.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_5_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_audio.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_classification.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_eagle.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_rm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_classification.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_next.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_next_mtp.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_vl_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/registry.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/roberta.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/sarashina2_vision.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/siglip.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/solar.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/stablelm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/starcoder2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/step3_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/torch_native_llama.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/transformers.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/vila.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/xverse.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/xverse_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/yivl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/mm_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/base_processor.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/clip.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/deepseek_vl_v2.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/dots_vlm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/gemma3.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/gemma3n.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/glm4v.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/internvl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/janus_pro.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/kimi_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/llava.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/minicpm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/mlama.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/mllama4.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/phi4mm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/pixtral.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/qwen_audio.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/qwen_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/sarashina2_vision.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/step3_vl.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/vila.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/offloader.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/operations.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/operations_strategy.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/code_completion_parser.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/conversation.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/harmony_parser.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/jinja_template_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/reasoning_parser.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/custom_logit_processor.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/frequency_penalty.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/min_new_tokens.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/orchestrator.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/presence_penalty.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/sampling_params.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/server_args_config_parser.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/single_batch_overlap.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/build_eagle_tree.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/ngram.cpp +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/ngram.h +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/ngram_cache.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/ngram_cache_binding.cpp +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/param.h +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/queue.h +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/eagle_info.py +0 -0
- /sglang-0.5.3/sglang/srt/speculative/ngram_utils.py → /sglang-0.5.3.post1/sglang/srt/speculative/ngram_info.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/spec_info.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/standalone_worker.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/tokenizer/tiktoken_tokenizer.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/torch_memory_saver_adapter.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/tracing/trace.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/patch_torch.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/poll_based_barrier.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/rpd_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/slow_rank_detector.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/warmup.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/weight_sync/tensor_bucket.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/weight_sync/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/__init__.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/test_flashattn_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/test_flashattn_mla_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/test_prefix_chunk_info.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/test_trtllm_mla_backend.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/doc_patch.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/few_shot_gsm8k.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/few_shot_gsm8k_engine.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/get_logits_ut.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/runners.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/send_one.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_common.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_gpqa.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_humaneval.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_math.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_mgsm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_mmlu.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_mmmu_vlm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_activation.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_block_fp8.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_block_fp8_deep_gemm_blackwell.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_custom_ops.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_cutlass_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_deepep_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_dynamic_grad_mode.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_fp4_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_layernorm.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_marlin_moe.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_marlin_utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_programs.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/utils.py +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang.egg-info/dependency_links.txt +0 -0
- {sglang-0.5.3 → sglang-0.5.3.post1}/sglang.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: sglang
|
3
|
-
Version: 0.5.3
|
3
|
+
Version: 0.5.3.post1
|
4
4
|
Summary: SGLang is a fast serving framework for large language models and vision language models.
|
5
5
|
License: Apache License
|
6
6
|
Version 2.0, January 2004
|
@@ -221,7 +221,7 @@ Requires-Dist: cuda-python
|
|
221
221
|
Requires-Dist: datasets
|
222
222
|
Requires-Dist: einops
|
223
223
|
Requires-Dist: fastapi
|
224
|
-
Requires-Dist: flashinfer_python==0.4.
|
224
|
+
Requires-Dist: flashinfer_python==0.4.0
|
225
225
|
Requires-Dist: hf_transfer
|
226
226
|
Requires-Dist: huggingface_hub
|
227
227
|
Requires-Dist: interegular
|
@@ -250,7 +250,7 @@ Requires-Dist: requests
|
|
250
250
|
Requires-Dist: scipy
|
251
251
|
Requires-Dist: sentencepiece
|
252
252
|
Requires-Dist: setproctitle
|
253
|
-
Requires-Dist: sgl-kernel==0.3.
|
253
|
+
Requires-Dist: sgl-kernel==0.3.15
|
254
254
|
Requires-Dist: soundfile==0.13.1
|
255
255
|
Requires-Dist: tiktoken
|
256
256
|
Requires-Dist: timm==1.0.16
|
@@ -263,7 +263,7 @@ Requires-Dist: tqdm
|
|
263
263
|
Requires-Dist: transformers==4.57.0
|
264
264
|
Requires-Dist: uvicorn
|
265
265
|
Requires-Dist: uvloop
|
266
|
-
Requires-Dist: xgrammar==0.1.
|
266
|
+
Requires-Dist: xgrammar==0.1.25
|
267
267
|
Requires-Dist: grpcio==1.75.1
|
268
268
|
Requires-Dist: grpcio-tools==1.75.1
|
269
269
|
Provides-Extra: decord
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
4
4
|
|
5
5
|
[project]
|
6
6
|
name = "sglang"
|
7
|
-
version = "0.5.3"
|
7
|
+
version = "0.5.3.post1"
|
8
8
|
description = "SGLang is a fast serving framework for large language models and vision language models."
|
9
9
|
readme = "README.md"
|
10
10
|
requires-python = ">=3.10"
|
@@ -24,7 +24,7 @@ dependencies = [
|
|
24
24
|
"datasets",
|
25
25
|
"einops",
|
26
26
|
"fastapi",
|
27
|
-
"flashinfer_python==0.4.
|
27
|
+
"flashinfer_python==0.4.0",
|
28
28
|
"hf_transfer",
|
29
29
|
"huggingface_hub",
|
30
30
|
"interegular",
|
@@ -53,7 +53,7 @@ dependencies = [
|
|
53
53
|
"scipy",
|
54
54
|
"sentencepiece",
|
55
55
|
"setproctitle",
|
56
|
-
"sgl-kernel==0.3.
|
56
|
+
"sgl-kernel==0.3.15",
|
57
57
|
"soundfile==0.13.1",
|
58
58
|
"tiktoken",
|
59
59
|
"timm==1.0.16",
|
@@ -66,7 +66,7 @@ dependencies = [
|
|
66
66
|
"transformers==4.57.0",
|
67
67
|
"uvicorn",
|
68
68
|
"uvloop",
|
69
|
-
"xgrammar==0.1.
|
69
|
+
"xgrammar==0.1.25",
|
70
70
|
"grpcio==1.75.1", # keep it align with compile_proto.py
|
71
71
|
"grpcio-tools==1.75.1" # keep it align with compile_proto.py
|
72
72
|
]
|
@@ -204,7 +204,6 @@ def prepare_inputs_for_correctness_test(bench_args, tokenizer, custom_prompts):
|
|
204
204
|
origin_input_ids=tmp_input_ids,
|
205
205
|
sampling_params=sampling_params,
|
206
206
|
)
|
207
|
-
req.prefix_indices = []
|
208
207
|
req.fill_ids = req.origin_input_ids
|
209
208
|
req.extend_input_len = len(req.fill_ids) - len(req.prefix_indices)
|
210
209
|
req.logprob_start_len = len(req.origin_input_ids) - 1
|
@@ -248,7 +247,6 @@ def prepare_synthetic_inputs_for_latency_test(
|
|
248
247
|
origin_input_ids=list(input_ids[i]),
|
249
248
|
sampling_params=sampling_params,
|
250
249
|
)
|
251
|
-
req.prefix_indices = []
|
252
250
|
req.fill_ids = req.origin_input_ids
|
253
251
|
req.extend_input_len = len(req.fill_ids) - len(req.prefix_indices)
|
254
252
|
req.logprob_start_len = len(req.origin_input_ids) - 1
|