sglang 0.4.6.post3__py3-none-any.whl → 0.4.6.post5__py3-none-any.whl
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/bench_offline_throughput.py +10 -8
- sglang/bench_one_batch.py +7 -6
- sglang/bench_one_batch_server.py +157 -21
- sglang/bench_serving.py +137 -59
- sglang/compile_deep_gemm.py +5 -5
- sglang/eval/loogle_eval.py +157 -0
- sglang/lang/chat_template.py +78 -78
- sglang/lang/tracer.py +1 -1
- sglang/srt/code_completion_parser.py +1 -1
- sglang/srt/configs/deepseekvl2.py +2 -2
- sglang/srt/configs/model_config.py +40 -28
- sglang/srt/constrained/base_grammar_backend.py +55 -72
- sglang/srt/constrained/llguidance_backend.py +25 -21
- sglang/srt/constrained/outlines_backend.py +27 -26
- sglang/srt/constrained/reasoner_grammar_backend.py +22 -33
- sglang/srt/constrained/xgrammar_backend.py +69 -43
- sglang/srt/conversation.py +49 -44
- sglang/srt/disaggregation/base/conn.py +1 -0
- sglang/srt/disaggregation/decode.py +129 -135
- sglang/srt/disaggregation/decode_schedule_batch_mixin.py +142 -0
- sglang/srt/disaggregation/fake/conn.py +3 -13
- sglang/srt/disaggregation/kv_events.py +357 -0
- sglang/srt/disaggregation/mini_lb.py +57 -24
- sglang/srt/disaggregation/mooncake/conn.py +238 -122
- sglang/srt/disaggregation/mooncake/transfer_engine.py +2 -1
- sglang/srt/disaggregation/nixl/conn.py +10 -19
- sglang/srt/disaggregation/prefill.py +132 -47
- sglang/srt/disaggregation/utils.py +123 -6
- sglang/srt/distributed/utils.py +3 -3
- sglang/srt/entrypoints/EngineBase.py +5 -0
- sglang/srt/entrypoints/engine.py +44 -9
- sglang/srt/entrypoints/http_server.py +23 -6
- sglang/srt/entrypoints/http_server_engine.py +5 -2
- sglang/srt/function_call/base_format_detector.py +250 -0
- sglang/srt/function_call/core_types.py +34 -0
- sglang/srt/function_call/deepseekv3_detector.py +157 -0
- sglang/srt/function_call/ebnf_composer.py +234 -0
- sglang/srt/function_call/function_call_parser.py +175 -0
- sglang/srt/function_call/llama32_detector.py +74 -0
- sglang/srt/function_call/mistral_detector.py +84 -0
- sglang/srt/function_call/pythonic_detector.py +163 -0
- sglang/srt/function_call/qwen25_detector.py +67 -0
- sglang/srt/function_call/utils.py +35 -0
- sglang/srt/hf_transformers_utils.py +46 -7
- sglang/srt/layers/attention/aiter_backend.py +513 -0
- sglang/srt/layers/attention/flashattention_backend.py +64 -18
- sglang/srt/layers/attention/flashinfer_mla_backend.py +8 -4
- sglang/srt/layers/attention/flashmla_backend.py +340 -78
- sglang/srt/layers/attention/triton_backend.py +3 -0
- sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py +1 -1
- sglang/srt/layers/attention/utils.py +6 -4
- sglang/srt/layers/attention/vision.py +1 -1
- sglang/srt/layers/communicator.py +451 -0
- sglang/srt/layers/dp_attention.py +61 -21
- sglang/srt/layers/layernorm.py +1 -1
- sglang/srt/layers/logits_processor.py +46 -11
- sglang/srt/layers/moe/cutlass_moe.py +207 -0
- sglang/srt/layers/moe/ep_moe/kernels.py +34 -12
- sglang/srt/layers/moe/ep_moe/layer.py +105 -51
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +82 -7
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +1 -1
- sglang/srt/layers/moe/fused_moe_triton/layer.py +14 -0
- sglang/srt/layers/moe/topk.py +67 -10
- sglang/srt/layers/multimodal.py +70 -0
- sglang/srt/layers/quantization/__init__.py +8 -3
- sglang/srt/layers/quantization/blockwise_int8.py +2 -2
- sglang/srt/layers/quantization/deep_gemm.py +77 -74
- sglang/srt/layers/quantization/fp8.py +92 -2
- sglang/srt/layers/quantization/fp8_kernel.py +3 -3
- sglang/srt/layers/quantization/fp8_utils.py +6 -0
- sglang/srt/layers/quantization/gptq.py +298 -6
- sglang/srt/layers/quantization/int8_kernel.py +20 -7
- sglang/srt/layers/quantization/qoq.py +244 -0
- sglang/srt/layers/sampler.py +0 -4
- sglang/srt/layers/vocab_parallel_embedding.py +18 -7
- sglang/srt/lora/lora_manager.py +2 -4
- sglang/srt/lora/mem_pool.py +4 -4
- sglang/srt/lora/triton_ops/gate_up_lora_b.py +1 -1
- sglang/srt/lora/triton_ops/qkv_lora_b.py +1 -1
- sglang/srt/lora/triton_ops/sgemm_lora_a.py +1 -1
- sglang/srt/lora/triton_ops/sgemm_lora_b.py +1 -1
- sglang/srt/lora/utils.py +1 -1
- sglang/srt/managers/data_parallel_controller.py +3 -3
- sglang/srt/managers/deepseek_eplb.py +278 -0
- sglang/srt/managers/detokenizer_manager.py +21 -8
- sglang/srt/managers/eplb_manager.py +55 -0
- sglang/srt/managers/expert_distribution.py +704 -56
- sglang/srt/managers/expert_location.py +394 -0
- sglang/srt/managers/expert_location_dispatch.py +91 -0
- sglang/srt/managers/io_struct.py +19 -4
- sglang/srt/managers/mm_utils.py +294 -140
- sglang/srt/managers/multimodal_processors/base_processor.py +127 -42
- sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py +6 -1
- sglang/srt/managers/multimodal_processors/gemma3.py +31 -6
- sglang/srt/managers/multimodal_processors/internvl.py +14 -5
- sglang/srt/managers/multimodal_processors/janus_pro.py +7 -1
- sglang/srt/managers/multimodal_processors/kimi_vl.py +7 -6
- sglang/srt/managers/multimodal_processors/llava.py +46 -0
- sglang/srt/managers/multimodal_processors/minicpm.py +25 -31
- sglang/srt/managers/multimodal_processors/mllama4.py +6 -0
- sglang/srt/managers/multimodal_processors/pixtral.py +127 -0
- sglang/srt/managers/multimodal_processors/qwen_vl.py +58 -16
- sglang/srt/managers/schedule_batch.py +122 -42
- sglang/srt/managers/schedule_policy.py +1 -5
- sglang/srt/managers/scheduler.py +205 -138
- sglang/srt/managers/scheduler_output_processor_mixin.py +124 -55
- sglang/srt/managers/session_controller.py +1 -1
- sglang/srt/managers/tokenizer_manager.py +232 -58
- sglang/srt/managers/tp_worker.py +12 -9
- sglang/srt/managers/tp_worker_overlap_thread.py +22 -11
- sglang/srt/mem_cache/base_prefix_cache.py +3 -0
- sglang/srt/mem_cache/chunk_cache.py +3 -1
- sglang/srt/mem_cache/hiradix_cache.py +4 -4
- sglang/srt/mem_cache/memory_pool.py +76 -52
- sglang/srt/mem_cache/multimodal_cache.py +45 -0
- sglang/srt/mem_cache/radix_cache.py +58 -5
- sglang/srt/metrics/collector.py +314 -39
- sglang/srt/mm_utils.py +10 -0
- sglang/srt/model_executor/cuda_graph_runner.py +29 -19
- sglang/srt/model_executor/expert_location_updater.py +422 -0
- sglang/srt/model_executor/forward_batch_info.py +5 -1
- sglang/srt/model_executor/model_runner.py +163 -68
- sglang/srt/model_loader/loader.py +10 -6
- sglang/srt/models/clip.py +5 -1
- sglang/srt/models/deepseek_janus_pro.py +2 -2
- sglang/srt/models/deepseek_v2.py +308 -351
- sglang/srt/models/exaone.py +8 -3
- sglang/srt/models/gemma3_mm.py +70 -33
- sglang/srt/models/llama.py +2 -0
- sglang/srt/models/llama4.py +15 -8
- sglang/srt/models/llava.py +258 -7
- sglang/srt/models/mimo_mtp.py +220 -0
- sglang/srt/models/minicpmo.py +5 -12
- sglang/srt/models/mistral.py +71 -1
- sglang/srt/models/mixtral.py +98 -34
- sglang/srt/models/mllama.py +3 -3
- sglang/srt/models/pixtral.py +467 -0
- sglang/srt/models/qwen2.py +95 -26
- sglang/srt/models/qwen2_5_vl.py +8 -0
- sglang/srt/models/qwen2_moe.py +330 -60
- sglang/srt/models/qwen2_vl.py +6 -0
- sglang/srt/models/qwen3.py +52 -10
- sglang/srt/models/qwen3_moe.py +411 -48
- sglang/srt/models/roberta.py +1 -1
- sglang/srt/models/siglip.py +294 -0
- sglang/srt/models/torch_native_llama.py +1 -1
- sglang/srt/openai_api/adapter.py +58 -20
- sglang/srt/openai_api/protocol.py +6 -8
- sglang/srt/operations.py +154 -0
- sglang/srt/operations_strategy.py +31 -0
- sglang/srt/reasoning_parser.py +3 -3
- sglang/srt/sampling/custom_logit_processor.py +18 -3
- sglang/srt/sampling/sampling_batch_info.py +4 -56
- sglang/srt/sampling/sampling_params.py +2 -2
- sglang/srt/server_args.py +162 -22
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +3 -3
- sglang/srt/speculative/eagle_utils.py +138 -7
- sglang/srt/speculative/eagle_worker.py +69 -21
- sglang/srt/utils.py +74 -17
- sglang/test/few_shot_gsm8k.py +2 -2
- sglang/test/few_shot_gsm8k_engine.py +2 -2
- sglang/test/run_eval.py +2 -2
- sglang/test/runners.py +8 -1
- sglang/test/send_one.py +13 -3
- sglang/test/simple_eval_common.py +1 -1
- sglang/test/simple_eval_humaneval.py +1 -1
- sglang/test/test_cutlass_moe.py +278 -0
- sglang/test/test_programs.py +5 -5
- sglang/test/test_utils.py +55 -14
- sglang/utils.py +3 -3
- sglang/version.py +1 -1
- {sglang-0.4.6.post3.dist-info → sglang-0.4.6.post5.dist-info}/METADATA +23 -13
- {sglang-0.4.6.post3.dist-info → sglang-0.4.6.post5.dist-info}/RECORD +178 -149
- {sglang-0.4.6.post3.dist-info → sglang-0.4.6.post5.dist-info}/WHEEL +1 -1
- sglang/srt/function_call_parser.py +0 -858
- sglang/srt/platforms/interface.py +0 -371
- /sglang/{llama3_eval.py → eval/llama3_eval.py} +0 -0
- /sglang/srt/models/{xiaomi_mimo.py → mimo.py} +0 -0
- {sglang-0.4.6.post3.dist-info → sglang-0.4.6.post5.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.6.post3.dist-info → sglang-0.4.6.post5.dist-info}/top_level.txt +0 -0
@@ -1,22 +1,23 @@
|
|
1
1
|
sglang/__init__.py,sha256=T-fZEjKP66Q1q3PB56oREs5U3zf6bL0fNcdIbW8jMhE,1652
|
2
2
|
sglang/api.py,sha256=vHiKBg8wwIdmrpnGclop5BzJ-1Q88emrlrfLwNCHg98,7010
|
3
|
-
sglang/bench_offline_throughput.py,sha256=
|
4
|
-
sglang/bench_one_batch.py,sha256=
|
5
|
-
sglang/bench_one_batch_server.py,sha256=
|
6
|
-
sglang/bench_serving.py,sha256=
|
3
|
+
sglang/bench_offline_throughput.py,sha256=j-h1Bk7zkI74EgFahfJnxe6aWtpdgKDfiN7qKmNN-0w,13895
|
4
|
+
sglang/bench_one_batch.py,sha256=fCxRRk14uQqTxpriBkrUkvrOUjNT7TZgDeGGWJQzhgw,19328
|
5
|
+
sglang/bench_one_batch_server.py,sha256=qFgN7tZwX4tK7KJeInrPvEtgF8DCQhTWr_l4jW0zH8w,11201
|
6
|
+
sglang/bench_serving.py,sha256=BdCY8iT5jM0s0T4DO8WmZaRyd2vKncALRx26Ptx3Yd0,64974
|
7
7
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
8
|
-
sglang/compile_deep_gemm.py,sha256=
|
8
|
+
sglang/compile_deep_gemm.py,sha256=H118s76CKdpZr-cDeFfBCePe7--c_teEBNVIzchYVSo,6243
|
9
9
|
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
10
10
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
11
|
-
sglang/
|
12
|
-
sglang/
|
13
|
-
sglang/
|
14
|
-
sglang/
|
11
|
+
sglang/utils.py,sha256=LJQksRakIH624rHwOfe9j91g1HzSOEiF0kymUGwMXu8,16176
|
12
|
+
sglang/version.py,sha256=B_ux4x0ePtuRu-TrL0kt2lDB2SlCBrlbrPC2KwVy6DY,28
|
13
|
+
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
14
|
+
sglang/eval/loogle_eval.py,sha256=pRPVA4fxGmT3_oXvXnlNE-UlPrcQGLBJF-OSE9YWJXM,4336
|
15
|
+
sglang/lang/chat_template.py,sha256=HKlx7snSWFED8GKF5ex79sQrPWFw5TSXQM0_LsiD9Bc,20552
|
15
16
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
16
17
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
17
18
|
sglang/lang/interpreter.py,sha256=OH1SFCm4rUCPO32MTo8j5V2Z13Jic7_r1GQOP1-aHaw,33234
|
18
19
|
sglang/lang/ir.py,sha256=gssBGxqQEVJmjR_PqG2yah48AsInGaO3CmnQ2boJThc,18769
|
19
|
-
sglang/lang/tracer.py,sha256=
|
20
|
+
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
20
21
|
sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
21
22
|
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
22
23
|
sglang/lang/backend/base_backend.py,sha256=tEutGCU5tni1xGlrIjAVvA9aflJBt2duKrIDzqabJWc,1975
|
@@ -26,23 +27,24 @@ sglang/lang/backend/runtime_endpoint.py,sha256=4pTG1TnOVTWBCh3rMhqL_NP2hsawG9xuP
|
|
26
27
|
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
27
28
|
sglang/srt/_custom_ops.py,sha256=L7NuEaRD_Q6Q54n0NZnLXgWZURbnn8Tkg4NQedE6zgA,3616
|
28
29
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
29
|
-
sglang/srt/code_completion_parser.py,sha256=
|
30
|
-
sglang/srt/conversation.py,sha256=
|
30
|
+
sglang/srt/code_completion_parser.py,sha256=vafJqdTTreD9kvCsoMuxP_fFmoue7pOA1ibI9KXg4mE,5405
|
31
|
+
sglang/srt/conversation.py,sha256=q2qX5plROHDwZYKDHhB4Cp1_xNQjolISaHCn1zdohIk,35297
|
31
32
|
sglang/srt/custom_op.py,sha256=J1PUcGaeJJjfAjp06BQsLpUkKyR1zsh9MvDiDlqqJsg,1129
|
32
|
-
sglang/srt/
|
33
|
-
sglang/srt/
|
34
|
-
sglang/srt/mm_utils.py,sha256=1ScBunw_x4W8ebM_AcJ62-1T2mfT8NlMJqdAhkF1lb0,12367
|
33
|
+
sglang/srt/hf_transformers_utils.py,sha256=NmsiIL2KvmPLX3QQYv4SuH5TM-WVB4En8WI-KUEWf7U,11733
|
34
|
+
sglang/srt/mm_utils.py,sha256=7o4w1W0VAWgEquVIz7qw7-IxYbZY2g3MrXw9php90oY,12621
|
35
35
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
36
|
+
sglang/srt/operations.py,sha256=LMxv7ZW5sFj4qGya3xmV_8uL95hUc0CjpMxEhWOgZsU,4252
|
37
|
+
sglang/srt/operations_strategy.py,sha256=_ml_3xdu6ytebCJ96an26Ys3mmLnlPETaXkUenpX6Kw,800
|
36
38
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
37
|
-
sglang/srt/reasoning_parser.py,sha256=
|
38
|
-
sglang/srt/server_args.py,sha256=
|
39
|
+
sglang/srt/reasoning_parser.py,sha256=lZN5b1TJp3EK2GzxcICQhp0tRQjQw3ROOrjRgQe6Bsc,6341
|
40
|
+
sglang/srt/server_args.py,sha256=YRr8CxIQAAiWxIDVxjTmXDyPxOvehSof9ylCd62Qix4,64106
|
39
41
|
sglang/srt/torch_memory_saver_adapter.py,sha256=HYlgYJ2sgmjs2RSjU2KbCaXijRg3mTDZ0ZcCB5Bt6Ps,2211
|
40
|
-
sglang/srt/utils.py,sha256=
|
42
|
+
sglang/srt/utils.py,sha256=ttLnrJ69dyppmRx8bIHrL4c6u9KY-xc_hj2kvjcRLk8,67598
|
41
43
|
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
42
44
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
43
45
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
44
46
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
45
|
-
sglang/srt/configs/deepseekvl2.py,sha256=
|
47
|
+
sglang/srt/configs/deepseekvl2.py,sha256=X8Q2gm7og_Ylx6tbFXetusfIJIXjWY_YH_p90C67BTI,23397
|
46
48
|
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
47
49
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
48
50
|
sglang/srt/configs/internvl.py,sha256=0wUu_ExziVaA6bJjJ6VKP1uFJOHlj6fVx6y5wLSqJvw,27722
|
@@ -50,7 +52,7 @@ sglang/srt/configs/janus_pro.py,sha256=Rrb7kQsNaUP-TiZrjNk8Lr1momFrql8ScEunnrH0_
|
|
50
52
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
51
53
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
52
54
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
53
|
-
sglang/srt/configs/model_config.py,sha256=
|
55
|
+
sglang/srt/configs/model_config.py,sha256=7qXt85m6dDp9qouFRSIN7mc0mWTTvOMNL5BgVYi1bUU,23843
|
54
56
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
55
57
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
56
58
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -60,30 +62,32 @@ sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8
|
|
60
62
|
sglang/srt/connector/serde/__init__.py,sha256=MvBJ7FBJtnou-AD-EdsCdAIDCcA8kWvUNuRViILVJ-0,718
|
61
63
|
sglang/srt/connector/serde/safe_serde.py,sha256=Iv_mFsDvk-cXuw0WTykBZ2yGxW0jb82DwVqC7r3RmAU,750
|
62
64
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
63
|
-
sglang/srt/constrained/base_grammar_backend.py,sha256=
|
64
|
-
sglang/srt/constrained/llguidance_backend.py,sha256=
|
65
|
-
sglang/srt/constrained/outlines_backend.py,sha256=
|
65
|
+
sglang/srt/constrained/base_grammar_backend.py,sha256=c7EbA6o_OlZTeUPkTcMVR0lNkZiCUo8C7ra5z7DJork,6822
|
66
|
+
sglang/srt/constrained/llguidance_backend.py,sha256=FP_Mafzb034Q62v19NZsdDQQ2iSl-dfLvCFuB8BsFFA,6117
|
67
|
+
sglang/srt/constrained/outlines_backend.py,sha256=P0EE0OoaJmxas0hnPN8Xz9vtST0J8f-wzuTsDY0aA2w,6864
|
66
68
|
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
67
|
-
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=
|
68
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=
|
69
|
+
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
70
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=FKWrMb1QSgtCTCyk6pQZ5NS-5T3M6dvdxN7OOPCYc8A,7837
|
69
71
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
70
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
71
|
-
sglang/srt/disaggregation/
|
72
|
-
sglang/srt/disaggregation/
|
73
|
-
sglang/srt/disaggregation/
|
72
|
+
sglang/srt/disaggregation/decode.py,sha256=SpKHH8xdG1_5XAgrd9YxOFVErmkp7e8gbRTCrsVYTys,25011
|
73
|
+
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=cUfd3-5lRHqWpwkrj4xdGMV2Hus08hdQbobTLNoCXlo,5569
|
74
|
+
sglang/srt/disaggregation/kv_events.py,sha256=SSB0zMeAwU2enA2YoEbWYdwUC3TJqEBo_V9SjqrmZHY,11380
|
75
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=r7oT02JtktxngiAA-uiW35EwUemBFRLqLrUsPZbQipg,14011
|
76
|
+
sglang/srt/disaggregation/prefill.py,sha256=M9sbLsHjVgJC6YRyGnQUfL7AZvviyot2d_aXSzc95nI,19591
|
77
|
+
sglang/srt/disaggregation/utils.py,sha256=vl5wY3wN6_4YAZ_8mH7EF-pop6EJJfrPVBCiFm2xCHU,9487
|
74
78
|
sglang/srt/disaggregation/base/__init__.py,sha256=KR8xXoRCDAy2U623mfP6ujXu42m1_F9EiudjrKu2I_A,130
|
75
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
79
|
+
sglang/srt/disaggregation/base/conn.py,sha256=hEOuR6kXrc7fRSYE9RAH53DLGHGaCcYWod6IkmtNttg,2491
|
76
80
|
sglang/srt/disaggregation/fake/__init__.py,sha256=zmfeKYXjonRhfFOck1c_mP7Q4cW5G0f1RsTwRivKu0s,47
|
77
|
-
sglang/srt/disaggregation/fake/conn.py,sha256=
|
81
|
+
sglang/srt/disaggregation/fake/conn.py,sha256=BzxFGjU87RgOeM_eV5S06RlB78DclpcYPlOAbcZKU2Y,2168
|
78
82
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=1vacEHmWjf7zgbMPzsXKB08FqNKNCquJdUiDlO41BOk,122
|
79
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
80
|
-
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=
|
83
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=31JWY7-xPqfQOsopP-3i8V8OUhwQP3OCOpQhYo239lk,33928
|
84
|
+
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=jsSn7PzPcC4OPHJU6BuUJBaiaatgiqZ5Ra25J_ATTmw,2789
|
81
85
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=n9HjrRk36WUcZNeetGWOh2pSriLp7GNTq7YYX9K3EtY,85
|
82
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
86
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=y67X1IutrzdqPYPzH9RUJ9vrTcIkOD1xk_PZWzJGIjM,29768
|
83
87
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
84
88
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
85
89
|
sglang/srt/distributed/parallel_state.py,sha256=cCQq94H8A-rO2wZf_bCf1lkwcTVOBrHubM9K1PrzVSY,51560
|
86
|
-
sglang/srt/distributed/utils.py,sha256=
|
90
|
+
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
87
91
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
88
92
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=qje-PQ3v8yaV-oYVLPws1mgIlXVsGKFCOvXHmSe8ZXg,19624
|
89
93
|
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=fLoptT_U0lVAqkhEg-ge53CdFSIKQpDRiqHYKwJVEZg,10974
|
@@ -93,53 +97,67 @@ sglang/srt/distributed/device_communicators/pynccl.py,sha256=obXyCaZznZHSt486XCn
|
|
93
97
|
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6EMz-oPS9J16WHo2Q_SRL1DtlJKK63Hfg,15349
|
94
98
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
95
99
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
96
|
-
sglang/srt/entrypoints/EngineBase.py,sha256=
|
97
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
98
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
99
|
-
sglang/srt/entrypoints/http_server_engine.py,sha256=
|
100
|
+
sglang/srt/entrypoints/EngineBase.py,sha256=6e7XecqeGAv29aiqCJyGsWYV8LwBNZN-lSxnUj9E_lw,1976
|
101
|
+
sglang/srt/entrypoints/engine.py,sha256=UEpN507ZGyOn1Mpi5PNk02vk0D8gieYF16EivfBC-FE,25360
|
102
|
+
sglang/srt/entrypoints/http_server.py,sha256=noIHojetylEVOQIoykHHondGlUyJUB4TQ7ZZvTK0TX8,31174
|
103
|
+
sglang/srt/entrypoints/http_server_engine.py,sha256=0QJFmrKAVnBmFbObHrmvUDcxDAsvnv6H29cQq286CKc,4939
|
100
104
|
sglang/srt/entrypoints/verl_engine.py,sha256=RYizNetTHzcB8dErX1EW4NsyRNGkFPljYaAf7pVRPdM,7002
|
105
|
+
sglang/srt/function_call/base_format_detector.py,sha256=76maa_oIMxLpnLGjcwXwVW6eFchVv4jIEFSCt0jDhxU,9842
|
106
|
+
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
107
|
+
sglang/srt/function_call/deepseekv3_detector.py,sha256=oDP5LNNcAHohGQjxFJoOJjx-karkOB7Y0VrYjUOAp0E,6636
|
108
|
+
sglang/srt/function_call/ebnf_composer.py,sha256=HuRg_sswglmgSF7GRZahKIku9ANH4MtAVRrBvoK5uuM,9788
|
109
|
+
sglang/srt/function_call/function_call_parser.py,sha256=X49mDuMD_9i8WqxzCFCwCbg0CLPmG_PAbDBT9se-mFo,6662
|
110
|
+
sglang/srt/function_call/llama32_detector.py,sha256=rWxtQ__guJOim_-E-RLOiykNuQGKB6wv-q2HpKugdeY,2660
|
111
|
+
sglang/srt/function_call/mistral_detector.py,sha256=jBK06utqq8u2OI7o3UiTINlBzk3KH6GxI0ouEtxFcP0,3342
|
112
|
+
sglang/srt/function_call/pythonic_detector.py,sha256=VD9eMGMZs3KkG3MMOlVDCusus8R7iDPKs6FvkMuMcdo,5953
|
113
|
+
sglang/srt/function_call/qwen25_detector.py,sha256=v1uLOzfH7N-WtXcanYpMuS2ZpiMfEUJSteql9mVDbfM,2380
|
114
|
+
sglang/srt/function_call/utils.py,sha256=iu4GWtIfcHv3vXZXkiPVsV1L7Hg-6BofBW2MTr8EEQM,891
|
101
115
|
sglang/srt/layers/activation.py,sha256=oSkdo8B8najXFcVay3Y__CEvgXh87lAIhG0CMp2Ugqs,5954
|
102
|
-
sglang/srt/layers/
|
116
|
+
sglang/srt/layers/communicator.py,sha256=pMateRTOfpub6zFWZnpdgGtBIwclZM7AX4Dwzbp0h9Y,16301
|
117
|
+
sglang/srt/layers/dp_attention.py,sha256=W8aPfuYXAXHGVccJVTk11871ixoDy67f3yqyd3MvFm0,9150
|
103
118
|
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
104
|
-
sglang/srt/layers/layernorm.py,sha256=
|
119
|
+
sglang/srt/layers/layernorm.py,sha256=kU47PX_V46RblaxxMNxWxGjWSa99o0w2s68908rGp6Q,5957
|
105
120
|
sglang/srt/layers/linear.py,sha256=nC9MxJrFap1BEyqgFlBySH4IeQruIbcBp32cOhUl5Fw,52149
|
106
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
121
|
+
sglang/srt/layers/logits_processor.py,sha256=eeG2zXZguvz2r1OVKVd5HFSPseL5fzRenh0cYuKO-GQ,25557
|
122
|
+
sglang/srt/layers/multimodal.py,sha256=Hsqrz4dyNH4GgkpzOxtuzPIDnxmtsj5ox0qcC4S2iio,2078
|
107
123
|
sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
|
108
124
|
sglang/srt/layers/pooler.py,sha256=nR9F4x0GP2KYkJihhcL-TX30gfLY3mVhOLRfeBDeKL4,1942
|
109
125
|
sglang/srt/layers/radix_attention.py,sha256=F71GgDes_fEt_cHxR9HM2QhNG5u7uF4zDAuLqwLYEV4,3481
|
110
126
|
sglang/srt/layers/rotary_embedding.py,sha256=eVBwYvGpFhL1KyyPutQuZotmvSpChcxzyhpmcbQ6cKQ,48267
|
111
|
-
sglang/srt/layers/sampler.py,sha256=
|
127
|
+
sglang/srt/layers/sampler.py,sha256=JmzceFPgl3vjaf9VQA3OPEW52tRZ_njrOxpGdZ35LP0,11261
|
112
128
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
113
129
|
sglang/srt/layers/utils.py,sha256=tkTz86DFZ4NRMEUc4QkYNskUskdxXoEqkWqaMGbhP7E,1045
|
114
|
-
sglang/srt/layers/vocab_parallel_embedding.py,sha256=
|
130
|
+
sglang/srt/layers/vocab_parallel_embedding.py,sha256=GPKCQiR2yH5Z2XSE9g3vWObdegcwPnMHXv7qEZovLH4,22755
|
131
|
+
sglang/srt/layers/attention/aiter_backend.py,sha256=xMTZ1J0OOMgvMaULrLHDMLUJaVUGAFm-OhAACVlGaYU,17893
|
115
132
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=lGujcYJ_CxHJy0Q9L6Phn3ds-nBGMy0OGj3R54R65iQ,3334
|
116
133
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=kCNn5Ub0jCsFjhVhuE-9qK53gu5a9oMStMeT2lcc6CU,9904
|
117
134
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
118
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
135
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=MuaEkGVuUfH50IeEqvwrVVl_2MSotnsSQ_UVxypkVm0,89610
|
119
136
|
sglang/srt/layers/attention/flashinfer_backend.py,sha256=53TXhmBpU5rs04-4u-yXclwJ5UYg7WJfyLDZJ8nSDOU,47651
|
120
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
121
|
-
sglang/srt/layers/attention/flashmla_backend.py,sha256=
|
137
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=DPVgahpGzd69HmtSyjPHusEub6RPYCZq8jzcuadAfHk,32468
|
138
|
+
sglang/srt/layers/attention/flashmla_backend.py,sha256=rOFJFTPOP0PMkD0z1J6MduJsYCRHpoHikgPtviL-iRU,20962
|
122
139
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
123
140
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=K5hUqBgakk2COSQqsaxWs0yEVOHS-7BlOygZTOeI8kE,9444
|
124
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
125
|
-
sglang/srt/layers/attention/utils.py,sha256=
|
126
|
-
sglang/srt/layers/attention/vision.py,sha256=
|
141
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=GH7EnR3caPrQQRyhSq15K1CRYC1wQ4kiDPHyS5gakqs,27093
|
142
|
+
sglang/srt/layers/attention/utils.py,sha256=KiRSIHaGBhErUhPWCSD3Uiaqb0pSEF0NJFwTTQXoMks,2887
|
143
|
+
sglang/srt/layers/attention/vision.py,sha256=rnfGrQPOQjSu3JV-rtdheQcR7jsvAF9P0-t5C9Nzudg,15358
|
127
144
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=DPu_aCPgwPqKWZPEQmp_xA7MPbpV2ip-MEICCB470Ao,19120
|
128
|
-
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=
|
145
|
+
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
129
146
|
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=m12jEnQkNJguATqvZ57HtMC2hhU4wqdB8xAYdh25BxE,13922
|
130
147
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
131
148
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
132
149
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
150
|
+
sglang/srt/layers/moe/cutlass_moe.py,sha256=rDDfx1Pzr0fILJQajid2DHuXQI6K8SToEbxM95nsW9Y,8565
|
133
151
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=U0qh3udHuJJll3udydqABoXPFz0au9aEj8Lv7OAHYvQ,4655
|
134
152
|
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
135
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
153
|
+
sglang/srt/layers/moe/topk.py,sha256=4LROSaYWkYY7PP5uMPInu8LzT42LkwyAA5lB6c7dntU,14210
|
136
154
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
137
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256
|
138
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
139
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=
|
155
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=-CXEAlgsWJEToxn2qmOPkm4m0opI7qhMCWACid1C0Xo,34206
|
156
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=Kg0PGNzVW_Ah_nLaNh7anooZ_uowV3Cj81l2f6fsk80,42259
|
157
|
+
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=zpbTtxcMZcRjx0ILd3EQ0H3zSEm9NbatZbAa6NdYOVY,24761
|
140
158
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
141
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
142
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
159
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=mNFBkSB9n1axyLAs9dsIwdAj7L5w9ZFEEDsxOL6XPPE,55996
|
160
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BoBiYHtUNOIvvXvqtWjHmx9i10SNbULi7l11YO9gHcs,25706
|
143
161
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
144
162
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
145
163
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ouRyZ5PEMPP2njPftCNhs-1g1y6wueWLmhI7G1SjV1k,4131
|
@@ -293,20 +311,21 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BMOV76fabrZcoyDmRpRbH11Jc
|
|
293
311
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json",sha256=-RzUWSIAAsg6iA-8SPMa68hPpBVoUyMJs3dLP7edRu0,4323
|
294
312
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
295
313
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Uz5X80VcNBOaxshwVNUEittHk2zqB4HQCfTJ4TPG5aM,3274
|
296
|
-
sglang/srt/layers/quantization/__init__.py,sha256=
|
314
|
+
sglang/srt/layers/quantization/__init__.py,sha256=fzlKUHBIQU8TsbzjAoFikdPKc4VXyv32ANF0EkO7XmA,12512
|
297
315
|
sglang/srt/layers/quantization/awq.py,sha256=KemDG55U3B6YZVjMV71awVAIj0islFvtxcUHmOBeGy0,6739
|
298
316
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
299
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=
|
300
|
-
sglang/srt/layers/quantization/deep_gemm.py,sha256=
|
301
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
302
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
303
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
304
|
-
sglang/srt/layers/quantization/gptq.py,sha256=
|
305
|
-
sglang/srt/layers/quantization/int8_kernel.py,sha256=
|
317
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=BgPrsTakDDFirALkW9q9VmFk0wFZv9cotkTU69Gnxeo,15122
|
318
|
+
sglang/srt/layers/quantization/deep_gemm.py,sha256=J9Brr0E0BEWFUrpTms_s7glPSXHCkaVS7YJKemWII8c,13214
|
319
|
+
sglang/srt/layers/quantization/fp8.py,sha256=9FC9HxqoekZF0YkIOZtngoVRvSYc0xKS7cqZ4L5jbq4,44220
|
320
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=OKpebbn09CpRzxFgB-RB_I4ZnWGLJ9nR0YTFu6-ZMdw,32570
|
321
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=wtgunvlmuYg_6wEA1_rd5BHRhGlWDmIRq6mIdpb5FIo,20234
|
322
|
+
sglang/srt/layers/quantization/gptq.py,sha256=d1frUjvXmZfQKkcMQY5t0BA4sXWHE9Jze24qxniptJE,26719
|
323
|
+
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
306
324
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
307
325
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
308
326
|
sglang/srt/layers/quantization/modelopt_quant.py,sha256=TpPgtbV7O5r1JY4Wm0np2pReQO6XERIdEDQcV41oTn0,16596
|
309
327
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=KtFr4lIslMA12yx4JjXXPOsa5OHjxXWA6scYCRQnFMQ,19483
|
328
|
+
sglang/srt/layers/quantization/qoq.py,sha256=adhsCixRUTh1m8sfpRWNhh5oX3I1WJli3Elg8uexP6A,8222
|
310
329
|
sglang/srt/layers/quantization/utils.py,sha256=AXvGD8KRZVVrkRR1Y64fGkz4lkUP-CAjAQdp0LDNXrE,5266
|
311
330
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=UFwlch8qEm2J4muM4hMATj06-rf-__lSbBqVr00j1tc,11459
|
312
331
|
sglang/srt/layers/quantization/w8a8_int8.py,sha256=MkvmcxQj3X5AZbx8pgnHYAikc_Xd_jOhJXaxx7255ho,8984
|
@@ -473,79 +492,86 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
473
492
|
sglang/srt/lora/layers.py,sha256=xdP2Gwlw9PCPZBhujGqO6aBn0eGxpVeIBFUp1LIGCto,13119
|
474
493
|
sglang/srt/lora/lora.py,sha256=uNvbjZ_Wr1SLI9-ElRJA_JKwkibSGroP5Bfpsr9MI-Y,7527
|
475
494
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
476
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
477
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
478
|
-
sglang/srt/lora/utils.py,sha256=
|
495
|
+
sglang/srt/lora/lora_manager.py,sha256=rn4dy99SREWL2GB4wH_e7POgnFrSkmOY-jCKmmX-974,11443
|
496
|
+
sglang/srt/lora/mem_pool.py,sha256=dIx_8yZiJkFMyddfKL9G0zzgDxdkCQjG2qrbdHxqPtA,9633
|
497
|
+
sglang/srt/lora/utils.py,sha256=S53SOjYqeEc9toqGaThod9MNWEJs0OJew6KY558cMF0,5250
|
479
498
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
480
499
|
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
481
500
|
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
482
501
|
sglang/srt/lora/triton_ops/__init__.py,sha256=JGOYPIn1XbGcyJTbt8A0qoc02PYONSGNNjGkC8yJpAM,283
|
483
|
-
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=
|
484
|
-
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=
|
485
|
-
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=
|
486
|
-
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=
|
502
|
+
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=vOUDzC_Sq7UGnDbdF8F7ChKG12hDIOFwwMb7e62Lz9w,5280
|
503
|
+
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=qCpJAksCSXS3Znm-ABx1QfrdNqj9hrP61oaeW-n2RhU,5945
|
504
|
+
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=yNBgl8jS76DPlGJg8puRkSnKkewf2_2oKfVZZRq4lYY,4351
|
505
|
+
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=EoF9HymgQ1V9DwyOJOvbw1hCbEjprVOne_fC4VHgj-s,4518
|
487
506
|
sglang/srt/managers/cache_controller.py,sha256=RDKuRuRdrMWhsy4QOXvtTG_u_NQUQFly7a6BnoEYiMY,18434
|
488
507
|
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
489
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=
|
490
|
-
sglang/srt/managers/
|
491
|
-
sglang/srt/managers/
|
492
|
-
sglang/srt/managers/
|
493
|
-
sglang/srt/managers/
|
508
|
+
sglang/srt/managers/data_parallel_controller.py,sha256=nB4CD_g8VShTZHCQ9sfst73lQeSvOChFzeY-6RRAhL8,11648
|
509
|
+
sglang/srt/managers/deepseek_eplb.py,sha256=bExIzjdX8IcBOWYdgne5n0VV9Vht6AfDPeBjQY1rttA,10699
|
510
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
511
|
+
sglang/srt/managers/eplb_manager.py,sha256=Th-CcIJjXdwAjja7WmXsc-41gjHyqUoHkeopSi17Jvw,2004
|
512
|
+
sglang/srt/managers/expert_distribution.py,sha256=lBqqULoM6WRr1pzN-2dDGMm3dMPMI3s1O98YlEiP1qk,24921
|
513
|
+
sglang/srt/managers/expert_location.py,sha256=IpmiHfU_2Zi7_pscMQsDJRzp9hwqEr9hDOs1Wh2zKzU,14656
|
514
|
+
sglang/srt/managers/expert_location_dispatch.py,sha256=GmQ2chTMCPJdkYydyent0hGXoQVGcDAmA0ZQt5Yq3LA,3461
|
515
|
+
sglang/srt/managers/io_struct.py,sha256=LEdefg_TOXeEglzXcui7f6Phyk_Yfb3IRdM8sYiX72E,32343
|
516
|
+
sglang/srt/managers/mm_utils.py,sha256=5sagb_LjLP6UOv5aXJiCTZHq5tJK95N01A3mOAMo9-4,24720
|
494
517
|
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
495
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
496
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
497
|
-
sglang/srt/managers/scheduler.py,sha256=
|
498
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=
|
499
|
-
sglang/srt/managers/session_controller.py,sha256=
|
500
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
501
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
502
|
-
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=
|
518
|
+
sglang/srt/managers/schedule_batch.py,sha256=GwbTqrq1anmayVeGl5UklRk6X45g5JlyeEAGhlnzpQU,68679
|
519
|
+
sglang/srt/managers/schedule_policy.py,sha256=6uRRgxbTJ0pztoAg8oRh2u1g6hNejDyMevD2-68zEYA,19723
|
520
|
+
sglang/srt/managers/scheduler.py,sha256=fScqhC7bQAy1BDtk4i5yeDDCCJMpXKhOF6RXDnoM_vY,93732
|
521
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=aaj0z1PD3fGIOPoTtWwqoKsii0yQCR7txVFXMPECveQ,29879
|
522
|
+
sglang/srt/managers/session_controller.py,sha256=Lh1kruMcKqR7WVWYJRZbYgowtsssVlP7_paIVXLLIcE,5756
|
523
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=MUTU2wZT3sFmB05Iej3Rs2EO896by6g1Gs-hBAeLfq4,59559
|
524
|
+
sglang/srt/managers/tp_worker.py,sha256=cnI2JRxDqM7RXaaXAnLHNyYH4Jt7SB6HLAD5fRoWoNA,10025
|
525
|
+
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=W-FP7dkR9_voS0emMj4N5ML3Iao9gNZc-on6iUflbrw,9835
|
503
526
|
sglang/srt/managers/utils.py,sha256=5i75uLlQOF_5CaT02CrWtwozMTtwTg2_nLP8Dtr-JZQ,1536
|
504
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=
|
527
|
+
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=D8TkKouzX4NSwziRNIoOzvf1mPIHoouDyHpHBRmBl6Y,14190
|
505
528
|
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
506
|
-
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=
|
507
|
-
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=
|
508
|
-
sglang/srt/managers/multimodal_processors/internvl.py,sha256=
|
509
|
-
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=
|
510
|
-
sglang/srt/managers/multimodal_processors/kimi_vl.py,sha256=
|
511
|
-
sglang/srt/managers/multimodal_processors/llava.py,sha256=
|
512
|
-
sglang/srt/managers/multimodal_processors/minicpm.py,sha256=
|
529
|
+
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=CMfhhdq7u6GzT8ZENo7ByClvQEx-HKaTGVgdYM1vMNw,3460
|
530
|
+
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=YUnVl7WA2inYV0QdBwb6mVIxqBRQorK2ivlB3nlX8PQ,3251
|
531
|
+
sglang/srt/managers/multimodal_processors/internvl.py,sha256=PYyumQeL8sxfzAlgYLErMX2GW3PT_IF3GJWDMjesSSg,9395
|
532
|
+
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=nSZYKLoCZtv7sQIM21KCt4jpnzVfcsF84m9CFPWwR7s,2058
|
533
|
+
sglang/srt/managers/multimodal_processors/kimi_vl.py,sha256=SNe8dXjZezksfd5YJWLhJsXofSYGsBKtd_kPYj51iBo,2641
|
534
|
+
sglang/srt/managers/multimodal_processors/llava.py,sha256=90D2A09EHgdWwapVSeLg5J4YsioeT2AvGmJkepZA-5I,8100
|
535
|
+
sglang/srt/managers/multimodal_processors/minicpm.py,sha256=2zHMSvMFvCkzk0v_SIaj1c_CJI7bYZ9we1HCukNb-lo,5544
|
513
536
|
sglang/srt/managers/multimodal_processors/mlama.py,sha256=MLiGS606LzVtdoXvjWGANx-K_7nE9J_fMVmkXN7Gz8k,1661
|
514
|
-
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=
|
515
|
-
sglang/srt/managers/multimodal_processors/
|
516
|
-
sglang/srt/
|
517
|
-
sglang/srt/mem_cache/
|
537
|
+
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=IAu09ZPMAHxZKsfGiKjZU_Fruj4AmKA0poqXC0zufWQ,5813
|
538
|
+
sglang/srt/managers/multimodal_processors/pixtral.py,sha256=uQJYbxhafNCmg0xP52FdElnkUatAyintER1XNuKz3b8,4195
|
539
|
+
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=hj_XWTjIALAcUuTVqln9GYWDpwFBJbzrDgq2tPYvTPQ,8709
|
540
|
+
sglang/srt/mem_cache/base_prefix_cache.py,sha256=WOUIY6ATzltzXQ7QXS9biSY2o_kzbpDIuTD4C6TLCQQ,1019
|
541
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=YFRsxPdLPrO550zww77mn29JF_I22ZBNyL_HA3aazQQ,2017
|
518
542
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
519
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
520
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
543
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=v2P-sl0gpucJZNDEhO0BdinWL270czE7uFZglOtuS30,16617
|
544
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=GymHdB7PQlGlXLgA9OfDbp6002cz1tXagwBIQkYpgK4,36293
|
545
|
+
sglang/srt/mem_cache/multimodal_cache.py,sha256=Q-lYcI-3HoLu0WJhE2F_An8g9mkZ8LwMrYnQ4383Rf0,1266
|
521
546
|
sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
|
522
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=
|
523
|
-
sglang/srt/metrics/collector.py,sha256=
|
547
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=foS7mmPCCUWDP12aQCZGw7XAJqYfzZTowkoCTOa7jjY,16656
|
548
|
+
sglang/srt/metrics/collector.py,sha256=YbFOQojvlzT6i6DqvH87vzVYZfZzhHHl0SLwG76kqfg,19585
|
524
549
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
525
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
526
|
-
sglang/srt/model_executor/
|
527
|
-
sglang/srt/model_executor/
|
550
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=QzYrlTkqxvqlPEoc9x0QhdxqtzK3pyjjuagt57NN4CM,26530
|
551
|
+
sglang/srt/model_executor/expert_location_updater.py,sha256=Wf_o-JPsUH81ZLCZvMkyxqaZngtU6PoVgVX2EMZEBFM,15791
|
552
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=3V5FKLj_dLL5pxy0FtcDZr2nUHGnyW8gRkx1GF7r7dM,27952
|
553
|
+
sglang/srt/model_executor/model_runner.py,sha256=bVrjXDzCAb3_H2dj2KbSvgO8wwdYrHKJ3ZGhcnu8eyo,52429
|
528
554
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
529
|
-
sglang/srt/model_loader/loader.py,sha256
|
555
|
+
sglang/srt/model_loader/loader.py,sha256=C2R_e-KbxrWK9v_bVC6U7eRG8SyJ2KxKyYmBx8BxbJ0,55650
|
530
556
|
sglang/srt/model_loader/utils.py,sha256=0NaMR67fESFopaklmsleiL27XH1QUrjZW246MUu1EJ0,1369
|
531
557
|
sglang/srt/model_loader/weight_utils.py,sha256=yKnau-wH9muczoCpDTCVIqXFqz-QJmEEySplX3bMJWk,32153
|
532
558
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
533
559
|
sglang/srt/models/bert.py,sha256=kHlErDgNX_mIhfWWCnAcH_ncvYg22Y61gI34gW8GuUY,12738
|
534
560
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
535
|
-
sglang/srt/models/clip.py,sha256=
|
561
|
+
sglang/srt/models/clip.py,sha256=mkdSNhc2SgRHyeq9tCLEjUGdnA8yS2EMMbMKSpn5dMs,19863
|
536
562
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
537
563
|
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
538
564
|
sglang/srt/models/deepseek.py,sha256=ZnN02HdgXCB23Vno5V9UMUoOxH5HC82vNTwsVulUJ-o,17206
|
539
|
-
sglang/srt/models/deepseek_janus_pro.py,sha256=
|
565
|
+
sglang/srt/models/deepseek_janus_pro.py,sha256=OeeI7vZbE4HGpxa8CwT6-Lbfs7J7WMQ3oBNpVJQpv3w,70450
|
540
566
|
sglang/srt/models/deepseek_nextn.py,sha256=Yy5dItwimszQsAN7EjgND2cNQ9bypJ1TtFfhqcBQJnk,5673
|
541
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
567
|
+
sglang/srt/models/deepseek_v2.py,sha256=iaFIKpi-_xfcv9Q18WZu7r9kCRZqYyTqApuO1SAvTXw,73855
|
542
568
|
sglang/srt/models/deepseek_vl2.py,sha256=j8BdxZsMjm6lPdbDipEIKhVIVywCP1Vl1Kl46BZ5_0Y,13147
|
543
|
-
sglang/srt/models/exaone.py,sha256=
|
569
|
+
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
544
570
|
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
545
571
|
sglang/srt/models/gemma2.py,sha256=kqtwdo93GWKm2iBN29RoIRH2ggRm-K_80LM5btgfBLo,16395
|
546
572
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
547
573
|
sglang/srt/models/gemma3_causal.py,sha256=LfwHhF0nRD7OnmeHXXfQ7rofnFXjJI74gZiptak18RY,24924
|
548
|
-
sglang/srt/models/gemma3_mm.py,sha256=
|
574
|
+
sglang/srt/models/gemma3_mm.py,sha256=EOW5Q0iOFvJWgpA1QdpwzVicVvv7RulERXWNtC-I_pQ,17004
|
549
575
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
550
576
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
551
577
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
@@ -555,71 +581,73 @@ sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8
|
|
555
581
|
sglang/srt/models/internvl.py,sha256=kEzkL5tAq3skvK5D7TqhiElSIXrA6cNOd8irYV4aKhA,24927
|
556
582
|
sglang/srt/models/kimi_vl.py,sha256=YoM6CmrF4ZS0SsXKiR-_SfylKhd87ciJjno6_x5LG4o,12874
|
557
583
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
558
|
-
sglang/srt/models/llama.py,sha256
|
559
|
-
sglang/srt/models/llama4.py,sha256=
|
584
|
+
sglang/srt/models/llama.py,sha256=-NC9EL9R8iJqaRrkMLewvTP3sgC_f07AHmGBVEdKmQ8,27149
|
585
|
+
sglang/srt/models/llama4.py,sha256=NwG0mBZQR4B6KVR-Xzp89UQYvVnFMOgkZKVWvtT7Jt4,19454
|
560
586
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
561
587
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
562
588
|
sglang/srt/models/llama_eagle3.py,sha256=KCvUrWn17t7T28G60HwMyy99iB9AbdbPnS2el9n3r6o,6804
|
563
589
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
564
590
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
565
|
-
sglang/srt/models/llava.py,sha256=
|
591
|
+
sglang/srt/models/llava.py,sha256=m0-qcEWEUyN7kIiCYJAZTi58MwL4ioqCAD99PSTpsuY,37496
|
566
592
|
sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc,12829
|
593
|
+
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
594
|
+
sglang/srt/models/mimo_mtp.py,sha256=y0wTNObGz0lyVt0zu7apdVlTRLEQmc_xsd8SvgSo_vo,7806
|
567
595
|
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
568
596
|
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
569
|
-
sglang/srt/models/minicpmo.py,sha256=
|
597
|
+
sglang/srt/models/minicpmo.py,sha256=umWgRpYqJchXyZOcz7LeBWIo6JatN4Wyr9bufcVmpbk,76060
|
570
598
|
sglang/srt/models/minicpmv.py,sha256=hSDWEcmutqOJv-xs0X_4TaNCDAWFUk71eRHLm9sPC0U,40564
|
571
|
-
sglang/srt/models/mistral.py,sha256=
|
572
|
-
sglang/srt/models/mixtral.py,sha256=
|
599
|
+
sglang/srt/models/mistral.py,sha256=z7q5NBVbQcboQTIwhULtsLpFvNferaIv49EzOXVgh7g,3487
|
600
|
+
sglang/srt/models/mixtral.py,sha256=n-Pz7fyWE4m6Uh7sjzAYKNr5Wy4QUj5Yekl0qiCwQI8,17055
|
573
601
|
sglang/srt/models/mixtral_quant.py,sha256=-kQw9r8KcLdO8SNN9RKXzrGq9Q2Al9l9cWHi1VrZSRM,15260
|
574
|
-
sglang/srt/models/mllama.py,sha256=
|
602
|
+
sglang/srt/models/mllama.py,sha256=pkS0UWiqKJHRsFtSZzpSI9O6B5_j1OtI5pf_nyDPp3U,39707
|
575
603
|
sglang/srt/models/mllama4.py,sha256=ejuhIVX0MDojdB5EPR-V-Qd_E9st8KYjnjyeArFbdFs,9084
|
576
604
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
577
605
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
578
606
|
sglang/srt/models/olmoe.py,sha256=TMzt-yB891bvA4X50xL0NjNnFYSx9imlA7N1EG8KNK0,15949
|
579
607
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
608
|
+
sglang/srt/models/pixtral.py,sha256=Iu7OTvM_nnApk1VjpUb1ucPBU2F1Kov5w6ddYn7gGqE,16983
|
580
609
|
sglang/srt/models/qwen.py,sha256=xYkVmMZS2uMqWhfndc8EYm0olpKFnggfuMp_6aobVi4,10758
|
581
|
-
sglang/srt/models/qwen2.py,sha256=
|
582
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
610
|
+
sglang/srt/models/qwen2.py,sha256=OBhNcpd2eSTceHFOjJFRBefv9WgZl0FkW5ErRNaKaME,18563
|
611
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=i35Gs0XJ8mnyDbXp_D1CmcQJoGS2Wly6BadeGI47Sjk,23031
|
583
612
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
584
613
|
sglang/srt/models/qwen2_eagle.py,sha256=Iz0HWL2FgSD3FqoFhfYmbIZeEYkPTJ96lYbkncmHJX4,4644
|
585
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
614
|
+
sglang/srt/models/qwen2_moe.py,sha256=6jsxIExxs6gd4rezTcP_yFtMlW4bwOWVGskVYQWfNxM,28822
|
586
615
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
587
|
-
sglang/srt/models/qwen2_vl.py,sha256=
|
588
|
-
sglang/srt/models/qwen3.py,sha256=
|
589
|
-
sglang/srt/models/qwen3_moe.py,sha256=
|
616
|
+
sglang/srt/models/qwen2_vl.py,sha256=Y-03fgF_8K0Ozd-GMgeCzfHHQS60aPDLfadZdRdy8g8,21311
|
617
|
+
sglang/srt/models/qwen3.py,sha256=lL39Ap6eY-7YFUrvLrd1cRcQ3zoUgYaI7D8Y9lb45Ls,13516
|
618
|
+
sglang/srt/models/qwen3_moe.py,sha256=6V3MCPhBc_gul2Qqu9d1cqoEt5YHXmo4jp48AxJN-i8,29457
|
590
619
|
sglang/srt/models/registry.py,sha256=inKh9iwOp3LFYm3nqujg-OtABClOP-ifc1stA9cZegA,3434
|
591
|
-
sglang/srt/models/roberta.py,sha256=
|
620
|
+
sglang/srt/models/roberta.py,sha256=77H_-9jtjqpHlpQhBuZXs7RUG-dSjauDkpHhFe61DpE,6320
|
621
|
+
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
592
622
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
593
|
-
sglang/srt/models/torch_native_llama.py,sha256=
|
594
|
-
sglang/srt/models/xiaomi_mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
623
|
+
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
595
624
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
596
625
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
597
626
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
598
|
-
sglang/srt/openai_api/adapter.py,sha256
|
599
|
-
sglang/srt/openai_api/protocol.py,sha256=
|
600
|
-
sglang/srt/
|
601
|
-
sglang/srt/sampling/
|
602
|
-
sglang/srt/sampling/
|
603
|
-
sglang/srt/sampling/sampling_params.py,sha256=xGo939Ai-_qUAvVEomZtuFN7U3Iro70Kpq42yXadyXk,6013
|
627
|
+
sglang/srt/openai_api/adapter.py,sha256=J8AHUwfCzai4d_fHGg92SA0evdn8IPTwH01u6XrEOj8,78334
|
628
|
+
sglang/srt/openai_api/protocol.py,sha256=6HnE8MZ5m2V78mJZ9Im9NyaD4FqC1WrJT8Ewx1iFySI,14459
|
629
|
+
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
630
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=VjOQpiXsY2vlTPtSb0T4piXIEtE54QefDpTVSDJ7bXE,11988
|
631
|
+
sglang/srt/sampling/sampling_params.py,sha256=tfUwWgxu6JWXsOClX_MFGTfetgRE63CQZsIpOhnWcoE,6013
|
604
632
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
605
633
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
606
634
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
607
635
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
608
636
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
609
637
|
sglang/srt/speculative/build_eagle_tree.py,sha256=lt4sXUehPi26MT2-2Z0VivtF6AP7kirSaEO_u-YJ4J4,11670
|
610
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
611
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
612
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
638
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=zQl6o6_T08UWIzkZbMghwVy_O2pLOyAYreM9VmyHRmY,9298
|
639
|
+
sglang/srt/speculative/eagle_utils.py,sha256=uENgCjXzPK--nynUBHKaSb5alRay6QvJ4hOn0BUxckE,33237
|
640
|
+
sglang/srt/speculative/eagle_worker.py,sha256=2k6ygbkJ1FK1I3vJNpvISQn8Ac3lW3i3xFRr1ZugIyY,28843
|
613
641
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
614
642
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
615
|
-
sglang/test/few_shot_gsm8k.py,sha256=
|
616
|
-
sglang/test/few_shot_gsm8k_engine.py,sha256=
|
617
|
-
sglang/test/run_eval.py,sha256=
|
618
|
-
sglang/test/runners.py,sha256=
|
619
|
-
sglang/test/send_one.py,sha256=
|
620
|
-
sglang/test/simple_eval_common.py,sha256=
|
643
|
+
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
644
|
+
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
645
|
+
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
646
|
+
sglang/test/runners.py,sha256=ryQXb7Jpg_ewqLSF9ZSy7BAwcB1gGeTBlw9MeknzTxE,30699
|
647
|
+
sglang/test/send_one.py,sha256=zIgnesgLDI3hcoZbYv4lpmizN44ZRmhShI2FbQauLrs,5003
|
648
|
+
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
621
649
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
622
|
-
sglang/test/simple_eval_humaneval.py,sha256=
|
650
|
+
sglang/test/simple_eval_humaneval.py,sha256=s8YuKIBkNUEOBP4XKsTMRdXGv5aRhl0oJyl-89lGk1w,5687
|
623
651
|
sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
|
624
652
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
625
653
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
@@ -627,17 +655,18 @@ sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGi
|
|
627
655
|
sglang/test/test_block_fp8.py,sha256=bsV6Y_tCUF2ROEmuPDegNmHzGF-T4AgOvH7eYmAmKtA,21604
|
628
656
|
sglang/test/test_block_fp8_ep.py,sha256=N1rvqbPErBaFFpeAw8TLYXGNZOoG7cfIBP2p5XbSyMo,10806
|
629
657
|
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
658
|
+
sglang/test/test_cutlass_moe.py,sha256=XPgC2wrXs04CEMVUKN362WBRIdWNZhFe_LYvCFlTBkY,9893
|
630
659
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
631
660
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
632
661
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
633
|
-
sglang/test/test_programs.py,sha256=
|
634
|
-
sglang/test/test_utils.py,sha256=
|
662
|
+
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
663
|
+
sglang/test/test_utils.py,sha256=7kMpQ28wvIb5_tJiH1J31FEOQ0aG-xJgPJI59c6iTYE,33859
|
635
664
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
636
665
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
637
666
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
638
667
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=er0i3KGHMkw-4UZB1GCFd4oYwRcXfU5wpO1ORqpNGGA,7626
|
639
|
-
sglang-0.4.6.
|
640
|
-
sglang-0.4.6.
|
641
|
-
sglang-0.4.6.
|
642
|
-
sglang-0.4.6.
|
643
|
-
sglang-0.4.6.
|
668
|
+
sglang-0.4.6.post5.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
669
|
+
sglang-0.4.6.post5.dist-info/METADATA,sha256=EAgGsHSr-8SE4rQOA2HRCN0L9H3TTbKAg_XIA8lBUW0,26727
|
670
|
+
sglang-0.4.6.post5.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
|
671
|
+
sglang-0.4.6.post5.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
672
|
+
sglang-0.4.6.post5.dist-info/RECORD,,
|