sglang 0.4.7__py3-none-any.whl → 0.4.8__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/__init__.py +2 -0
- sglang/api.py +7 -0
- sglang/bench_one_batch.py +8 -6
- sglang/bench_serving.py +1 -1
- sglang/lang/interpreter.py +40 -1
- sglang/lang/ir.py +27 -0
- sglang/math_utils.py +8 -0
- sglang/srt/_custom_ops.py +2 -2
- sglang/srt/code_completion_parser.py +2 -44
- sglang/srt/configs/model_config.py +6 -0
- sglang/srt/constants.py +3 -0
- sglang/srt/conversation.py +19 -3
- sglang/srt/custom_op.py +5 -1
- sglang/srt/disaggregation/base/__init__.py +1 -1
- sglang/srt/disaggregation/base/conn.py +25 -11
- sglang/srt/disaggregation/common/__init__.py +5 -1
- sglang/srt/disaggregation/common/utils.py +42 -0
- sglang/srt/disaggregation/decode.py +211 -72
- sglang/srt/disaggregation/decode_schedule_batch_mixin.py +4 -3
- sglang/srt/disaggregation/fake/__init__.py +1 -1
- sglang/srt/disaggregation/fake/conn.py +15 -9
- sglang/srt/disaggregation/mini_lb.py +34 -4
- sglang/srt/disaggregation/mooncake/__init__.py +1 -1
- sglang/srt/disaggregation/mooncake/conn.py +30 -29
- sglang/srt/disaggregation/nixl/__init__.py +6 -1
- sglang/srt/disaggregation/nixl/conn.py +17 -12
- sglang/srt/disaggregation/prefill.py +144 -55
- sglang/srt/disaggregation/utils.py +155 -123
- sglang/srt/distributed/parallel_state.py +12 -4
- sglang/srt/entrypoints/engine.py +37 -29
- sglang/srt/entrypoints/http_server.py +153 -72
- sglang/srt/entrypoints/http_server_engine.py +0 -3
- sglang/srt/entrypoints/openai/__init__.py +0 -0
- sglang/srt/{openai_api → entrypoints/openai}/protocol.py +84 -10
- sglang/srt/entrypoints/openai/serving_base.py +149 -0
- sglang/srt/entrypoints/openai/serving_chat.py +921 -0
- sglang/srt/entrypoints/openai/serving_completions.py +424 -0
- sglang/srt/entrypoints/openai/serving_embedding.py +169 -0
- sglang/srt/entrypoints/openai/serving_rerank.py +102 -0
- sglang/srt/entrypoints/openai/serving_score.py +61 -0
- sglang/srt/entrypoints/openai/usage_processor.py +81 -0
- sglang/srt/entrypoints/openai/utils.py +72 -0
- sglang/srt/eplb_simulator/__init__.py +1 -0
- sglang/srt/eplb_simulator/reader.py +51 -0
- sglang/srt/function_call/base_format_detector.py +7 -4
- sglang/srt/function_call/deepseekv3_detector.py +1 -1
- sglang/srt/function_call/ebnf_composer.py +64 -10
- sglang/srt/function_call/function_call_parser.py +6 -6
- sglang/srt/function_call/llama32_detector.py +1 -1
- sglang/srt/function_call/mistral_detector.py +1 -1
- sglang/srt/function_call/pythonic_detector.py +1 -1
- sglang/srt/function_call/qwen25_detector.py +1 -1
- sglang/srt/{openai_api/utils.py → jinja_template_utils.py} +6 -5
- sglang/srt/layers/activation.py +40 -3
- sglang/srt/layers/attention/aiter_backend.py +20 -4
- sglang/srt/layers/attention/base_attn_backend.py +1 -1
- sglang/srt/layers/attention/cutlass_mla_backend.py +39 -15
- sglang/srt/layers/attention/flashattention_backend.py +71 -72
- sglang/srt/layers/attention/flashinfer_backend.py +10 -8
- sglang/srt/layers/attention/flashinfer_mla_backend.py +29 -28
- sglang/srt/layers/attention/flashmla_backend.py +7 -12
- sglang/srt/layers/attention/tbo_backend.py +3 -3
- sglang/srt/layers/attention/triton_backend.py +138 -130
- sglang/srt/layers/attention/triton_ops/decode_attention.py +2 -7
- sglang/srt/layers/attention/vision.py +51 -24
- sglang/srt/layers/communicator.py +28 -10
- sglang/srt/layers/dp_attention.py +11 -2
- sglang/srt/layers/layernorm.py +29 -2
- sglang/srt/layers/linear.py +0 -4
- sglang/srt/layers/logits_processor.py +2 -14
- sglang/srt/layers/moe/ep_moe/kernels.py +165 -7
- sglang/srt/layers/moe/ep_moe/layer.py +249 -33
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +11 -37
- 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 +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +7 -4
- sglang/srt/layers/moe/fused_moe_triton/layer.py +75 -12
- sglang/srt/layers/moe/topk.py +107 -12
- sglang/srt/layers/pooler.py +56 -0
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +6 -2
- sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py +1 -0
- sglang/srt/layers/quantization/{deep_gemm.py → deep_gemm_wrapper/compile_utils.py} +23 -80
- sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +32 -0
- sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py +110 -0
- sglang/srt/layers/quantization/fp8.py +25 -17
- sglang/srt/layers/quantization/fp8_kernel.py +44 -15
- sglang/srt/layers/quantization/fp8_utils.py +87 -22
- sglang/srt/layers/quantization/modelopt_quant.py +62 -8
- sglang/srt/layers/quantization/utils.py +5 -2
- sglang/srt/layers/radix_attention.py +2 -3
- sglang/srt/layers/rotary_embedding.py +42 -2
- sglang/srt/layers/sampler.py +1 -1
- sglang/srt/lora/lora_manager.py +249 -105
- sglang/srt/lora/mem_pool.py +53 -50
- sglang/srt/lora/utils.py +1 -1
- sglang/srt/managers/cache_controller.py +33 -14
- sglang/srt/managers/io_struct.py +31 -10
- sglang/srt/managers/multimodal_processors/base_processor.py +2 -2
- sglang/srt/managers/multimodal_processors/vila.py +85 -0
- sglang/srt/managers/schedule_batch.py +79 -37
- sglang/srt/managers/schedule_policy.py +70 -56
- sglang/srt/managers/scheduler.py +220 -79
- sglang/srt/managers/template_manager.py +226 -0
- sglang/srt/managers/tokenizer_manager.py +40 -10
- sglang/srt/managers/tp_worker.py +12 -2
- sglang/srt/managers/tp_worker_overlap_thread.py +11 -0
- sglang/srt/mem_cache/{paged_allocator.py → allocator.py} +125 -34
- sglang/srt/mem_cache/base_prefix_cache.py +52 -8
- sglang/srt/mem_cache/chunk_cache.py +11 -15
- sglang/srt/mem_cache/hiradix_cache.py +38 -25
- sglang/srt/mem_cache/memory_pool.py +213 -505
- sglang/srt/mem_cache/memory_pool_host.py +380 -0
- sglang/srt/mem_cache/radix_cache.py +56 -28
- sglang/srt/model_executor/cuda_graph_runner.py +198 -100
- sglang/srt/model_executor/forward_batch_info.py +32 -10
- sglang/srt/model_executor/model_runner.py +28 -12
- sglang/srt/model_loader/loader.py +16 -2
- sglang/srt/model_loader/weight_utils.py +11 -2
- sglang/srt/models/bert.py +113 -13
- sglang/srt/models/deepseek_nextn.py +29 -27
- sglang/srt/models/deepseek_v2.py +213 -173
- sglang/srt/models/glm4.py +312 -0
- sglang/srt/models/internvl.py +46 -102
- sglang/srt/models/mimo_mtp.py +2 -18
- sglang/srt/models/roberta.py +117 -9
- sglang/srt/models/vila.py +305 -0
- sglang/srt/reasoning_parser.py +21 -11
- sglang/srt/sampling/sampling_batch_info.py +24 -0
- sglang/srt/sampling/sampling_params.py +2 -0
- sglang/srt/server_args.py +351 -238
- sglang/srt/speculative/build_eagle_tree.py +1 -1
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +131 -9
- sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +130 -14
- sglang/srt/speculative/eagle_utils.py +468 -116
- sglang/srt/speculative/eagle_worker.py +258 -84
- sglang/srt/torch_memory_saver_adapter.py +19 -15
- sglang/srt/two_batch_overlap.py +4 -2
- sglang/srt/utils.py +235 -11
- sglang/test/attention/test_prefix_chunk_info.py +2 -0
- sglang/test/runners.py +38 -3
- sglang/test/test_block_fp8.py +1 -0
- sglang/test/test_block_fp8_deep_gemm_blackwell.py +252 -0
- sglang/test/test_block_fp8_ep.py +2 -0
- sglang/test/test_utils.py +4 -1
- sglang/utils.py +9 -0
- sglang/version.py +1 -1
- {sglang-0.4.7.dist-info → sglang-0.4.8.dist-info}/METADATA +8 -14
- {sglang-0.4.7.dist-info → sglang-0.4.8.dist-info}/RECORD +150 -128
- sglang/srt/entrypoints/verl_engine.py +0 -179
- sglang/srt/openai_api/adapter.py +0 -1990
- {sglang-0.4.7.dist-info → sglang-0.4.8.dist-info}/WHEEL +0 -0
- {sglang-0.4.7.dist-info → sglang-0.4.8.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.7.dist-info → sglang-0.4.8.dist-info}/top_level.txt +0 -0
@@ -1,23 +1,24 @@
|
|
1
|
-
sglang/__init__.py,sha256=
|
2
|
-
sglang/api.py,sha256=
|
1
|
+
sglang/__init__.py,sha256=x1v8748WXS2BAptWAd5fR3YBEkngC7e_P_rkCNuNCGg,1702
|
2
|
+
sglang/api.py,sha256=rcp3GeoyZhmJ0GDLPRkuZNcxd0TBJy_wfUDpcmQoqW8,7210
|
3
3
|
sglang/bench_offline_throughput.py,sha256=TwgXZYmwPaHVsdPtNU9LO0p1tr5OOKLy9wYgrfGAlFU,14056
|
4
|
-
sglang/bench_one_batch.py,sha256=
|
4
|
+
sglang/bench_one_batch.py,sha256=RJsXQ7pvq8y4yzW7svURtWZF5RiawxEMrsjV0OcKsrk,19388
|
5
5
|
sglang/bench_one_batch_server.py,sha256=4Jbs8UI-Sbt3TL3SJBC3fySZPe4apz2glKWOvvaYsQQ,13486
|
6
|
-
sglang/bench_serving.py,sha256=
|
6
|
+
sglang/bench_serving.py,sha256=EzZn91DuScAEhUMQv-LPWm3UoGjzj8OEzHMzVwoEA34,65672
|
7
7
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
8
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/math_utils.py,sha256=QYtbaIA76P33ojcOrL32VR6yXWv-Od_3WCZNO4kQ-YQ,177
|
11
12
|
sglang/profiler.py,sha256=tEHzHerXC-ymk4OrkoUcMbgcGHmb8VESthsNSP2Yx9w,4417
|
12
|
-
sglang/utils.py,sha256=
|
13
|
-
sglang/version.py,sha256=
|
13
|
+
sglang/utils.py,sha256=VH6zrnkjzcR3DE__WfVph6wswJ4JuzoQD47VmbZ38eI,16435
|
14
|
+
sglang/version.py,sha256=40-PUZPRIakJU2yYWQcwTYvSJA6iewqiG8XylhxuAQk,22
|
14
15
|
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
15
16
|
sglang/eval/loogle_eval.py,sha256=pRPVA4fxGmT3_oXvXnlNE-UlPrcQGLBJF-OSE9YWJXM,4336
|
16
17
|
sglang/lang/chat_template.py,sha256=HKlx7snSWFED8GKF5ex79sQrPWFw5TSXQM0_LsiD9Bc,20552
|
17
18
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
18
19
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
19
|
-
sglang/lang/interpreter.py,sha256=
|
20
|
-
sglang/lang/ir.py,sha256=
|
20
|
+
sglang/lang/interpreter.py,sha256=JneG-Yw-XyOTBZCIoxTiQluQjAlSz1YswnV0l6pqVPo,34811
|
21
|
+
sglang/lang/ir.py,sha256=FnRJ-lndAsR4GR0ONJRPDtlYx8FvL9RIk44vSA16RBk,19656
|
21
22
|
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
22
23
|
sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
23
24
|
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
@@ -26,23 +27,25 @@ sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThc
|
|
26
27
|
sglang/lang/backend/openai.py,sha256=YFs7pCDK6_DoYmjTa-vgDVdaeE4PYr7E-sIC1q7vAns,16422
|
27
28
|
sglang/lang/backend/runtime_endpoint.py,sha256=oxLCLXCa26VfKyPV-wbRjLrQvqTG8NzoaVgwczzyIYc,17481
|
28
29
|
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
29
|
-
sglang/srt/_custom_ops.py,sha256=
|
30
|
+
sglang/srt/_custom_ops.py,sha256=0lJRMTKTjoxJPh1qQnnMY02Z3SyBDi7LJI34IBLQsgQ,4462
|
30
31
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
31
|
-
sglang/srt/code_completion_parser.py,sha256=
|
32
|
-
sglang/srt/
|
33
|
-
sglang/srt/
|
32
|
+
sglang/srt/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
33
|
+
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
34
|
+
sglang/srt/conversation.py,sha256=9Ix1NRQAErjXen8s4Yobb1HKizln7VBdrZPK_QKONoY,37104
|
35
|
+
sglang/srt/custom_op.py,sha256=At-Nqm_noJyoxi928TLvIPzUgj3DM-St-g2mdx1CWEI,2912
|
34
36
|
sglang/srt/debug_utils.py,sha256=slaFOY4BYDBFatkfu8FZlzai-u4LFS-5GUzdr-t50zE,2241
|
35
37
|
sglang/srt/hf_transformers_utils.py,sha256=S1ZF4aFKTocenXvj9ti6M-buiCBus4FrP1AdwFz_Wbw,11943
|
38
|
+
sglang/srt/jinja_template_utils.py,sha256=Jc6Vl-lYtUyMBSWWQGIMpJQ1O-ceU9c8DbOi_bN-oVk,6719
|
36
39
|
sglang/srt/mm_utils.py,sha256=7o4w1W0VAWgEquVIz7qw7-IxYbZY2g3MrXw9php90oY,12621
|
37
40
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
38
41
|
sglang/srt/operations.py,sha256=ddQ8KO63L73OciaR8MZ9h2h83gKVY4-WuWgeEGowPJA,5346
|
39
42
|
sglang/srt/operations_strategy.py,sha256=6DDLEdmkLrFDTXWZoFO0q9MZjEThvfyvoO-LbQsNpPQ,7023
|
40
43
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
41
|
-
sglang/srt/reasoning_parser.py,sha256=
|
42
|
-
sglang/srt/server_args.py,sha256=
|
43
|
-
sglang/srt/torch_memory_saver_adapter.py,sha256=
|
44
|
-
sglang/srt/two_batch_overlap.py,sha256=
|
45
|
-
sglang/srt/utils.py,sha256=
|
44
|
+
sglang/srt/reasoning_parser.py,sha256=vf0kWBM4IXwbuzGBIOMdiXdn9gavqkHb1QIaTbkU7vc,6742
|
45
|
+
sglang/srt/server_args.py,sha256=HCjiKk1VujrWMR2SPiO2bzgdnySGZO34PaoSeCM-pEw,72873
|
46
|
+
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
47
|
+
sglang/srt/two_batch_overlap.py,sha256=Q6tobqItnlK5ad9mqqMMx0HJ-PAzW4DgBtgSQ7Ax6sM,21848
|
48
|
+
sglang/srt/utils.py,sha256=kQWtZ0JUyaYDJNW-zNV0AU7Yfn9qGnRztPoSM5gC8sE,78080
|
46
49
|
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
47
50
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
48
51
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -55,7 +58,7 @@ sglang/srt/configs/janus_pro.py,sha256=Rrb7kQsNaUP-TiZrjNk8Lr1momFrql8ScEunnrH0_
|
|
55
58
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
56
59
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
57
60
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
58
|
-
sglang/srt/configs/model_config.py,sha256=
|
61
|
+
sglang/srt/configs/model_config.py,sha256=mXERUkexcWnZxrCzpxaMo7FhYm-CNhwttDIVhw-ZysY,25206
|
59
62
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
60
63
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
61
64
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -72,27 +75,28 @@ sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCX
|
|
72
75
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
73
76
|
sglang/srt/constrained/xgrammar_backend.py,sha256=u9Ao-XX22UzALkATEAR_-0EoyBTxMTJV590qd9LAUHM,7906
|
74
77
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
75
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
76
|
-
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=
|
78
|
+
sglang/srt/disaggregation/decode.py,sha256=GLIaPpm3I3oykq3A41Ru4gdsLa9LwUADc3xqM2LuHSU,33335
|
79
|
+
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=8UdNaj8KKMLV5Cydhw8gnHM-zRrnKM_AAd3Qc-SRfWg,5648
|
77
80
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
78
81
|
sglang/srt/disaggregation/launch_lb.py,sha256=mcbAztN4gnHevw_T5R2_nWsymsDEY9vHkm7OJ1vr6cc,4211
|
79
|
-
sglang/srt/disaggregation/mini_lb.py,sha256=
|
80
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
81
|
-
sglang/srt/disaggregation/utils.py,sha256=
|
82
|
-
sglang/srt/disaggregation/base/__init__.py,sha256=
|
83
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
84
|
-
sglang/srt/disaggregation/common/__init__.py,sha256=
|
82
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=BBeIdeZZxi7Ra5_hukHHX3TNdyfZ4tP1GBUxC-qrv_g,14401
|
83
|
+
sglang/srt/disaggregation/prefill.py,sha256=SQYLDpanJNc8sJHXQoPD6P48HGAEigxdf2CVal3Nl40,23419
|
84
|
+
sglang/srt/disaggregation/utils.py,sha256=84EF9I0lOK8bWqd8cbTTgVDzG6ecofp6WuSVqgCe1jc,11386
|
85
|
+
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
86
|
+
sglang/srt/disaggregation/base/conn.py,sha256=6KK_7HL7xixVSB8iap8jjJrIv3JgHDmynZ39Os3k5MU,2771
|
87
|
+
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
85
88
|
sglang/srt/disaggregation/common/conn.py,sha256=CZR1lMCE_mpSkvjc6BBmSr1SbHY1uZuxjpanazD-YXc,16071
|
86
|
-
sglang/srt/disaggregation/
|
87
|
-
sglang/srt/disaggregation/fake/
|
88
|
-
sglang/srt/disaggregation/
|
89
|
-
sglang/srt/disaggregation/mooncake/
|
89
|
+
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
90
|
+
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
91
|
+
sglang/srt/disaggregation/fake/conn.py,sha256=oD1DArn1yDFZCu-X6p93uSLlAXEkt9lYxERICMznxGw,2286
|
92
|
+
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
93
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=ES9N4J_zy5xdG8_YEsrcodXZPCBwKf9SBddOBCGLOHc,47837
|
90
94
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=gOcjZPtksJDq4iiIs0_zREdOM8trqUcmOXkrj-wiCuU,3149
|
91
|
-
sglang/srt/disaggregation/nixl/__init__.py,sha256=
|
92
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
95
|
+
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
96
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=KzVPRH8MaOAiG9EdfDN31sE9U9Ibsj2McDlSRWzHiP0,18055
|
93
97
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
94
98
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
95
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
99
|
+
sglang/srt/distributed/parallel_state.py,sha256=0_G1TtBOFMYDix5rfuEHYBMpy9A-OuPs9yFd5nCiZ8Q,53927
|
96
100
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
97
101
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
98
102
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=qje-PQ3v8yaV-oYVLPws1mgIlXVsGKFCOvXHmSe8ZXg,19624
|
@@ -105,52 +109,63 @@ sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6
|
|
105
109
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
106
110
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
107
111
|
sglang/srt/entrypoints/EngineBase.py,sha256=FCwqQMJE_8CCCMThAXUZaKafsHvh2BaQ31J-7_ormwA,2310
|
108
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
109
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
110
|
-
sglang/srt/entrypoints/http_server_engine.py,sha256=
|
111
|
-
sglang/srt/entrypoints/
|
112
|
-
sglang/srt/
|
112
|
+
sglang/srt/entrypoints/engine.py,sha256=oNcZDupOYllUjtYnNZOuOqfQzxg3SonwC4jNn-ByvQY,30169
|
113
|
+
sglang/srt/entrypoints/http_server.py,sha256=Fyb3z9OKXF9h_-duhWsHLjZayE3uoZ2dHpeV757bxXc,34745
|
114
|
+
sglang/srt/entrypoints/http_server_engine.py,sha256=ncN45ti9mawSOimPSedI6zugfoMhMQOYh4tmdfC9LcE,4936
|
115
|
+
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
116
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=JepHGUD8DcwNJQ0B2YnR6ZvWp6fhc4IQa2zQthBI8z4,17110
|
117
|
+
sglang/srt/entrypoints/openai/serving_base.py,sha256=5NJ2S_6B2NFSwn4nLp6eaeJ5iC3IcQzMEY9lW_gPcdA,5246
|
118
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=ojMNf55Nq-WVpwhl7TQdwepyb1JShfKJkzgfWCPH1UE,36542
|
119
|
+
sglang/srt/entrypoints/openai/serving_completions.py,sha256=7JKbykpFYnqsmej6iK_SHnD67IJ7KOVBbl11TVtKPPg,16661
|
120
|
+
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=ZAX4qQ9YZ7qUvT6zCAfrGFtkEfydPHiWuoPDz2Qrr2I,6245
|
121
|
+
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
122
|
+
sglang/srt/entrypoints/openai/serving_score.py,sha256=ebAts-m6Pq-LTgFKwggkywBUrAgUSppHHVEzgwYHUzo,1955
|
123
|
+
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
124
|
+
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
125
|
+
sglang/srt/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6OiOZEtHpltyzzjY,21
|
126
|
+
sglang/srt/eplb_simulator/reader.py,sha256=R9wV7PqaCjILSnfYk90hNY95iJeST08a55Uj2Qk4iE0,1832
|
127
|
+
sglang/srt/function_call/base_format_detector.py,sha256=eMSqbx99YPm2m_ChLafFRuLOzXBtA0oJn_Q4FtB3FnM,12950
|
113
128
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
114
|
-
sglang/srt/function_call/deepseekv3_detector.py,sha256=
|
115
|
-
sglang/srt/function_call/ebnf_composer.py,sha256=
|
116
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
117
|
-
sglang/srt/function_call/llama32_detector.py,sha256=
|
118
|
-
sglang/srt/function_call/mistral_detector.py,sha256=
|
119
|
-
sglang/srt/function_call/pythonic_detector.py,sha256=
|
120
|
-
sglang/srt/function_call/qwen25_detector.py,sha256=
|
129
|
+
sglang/srt/function_call/deepseekv3_detector.py,sha256=XudIiIt2Mejokg6qOkX7vYS-3XIFstOBHv-m-Q5fBLQ,8970
|
130
|
+
sglang/srt/function_call/ebnf_composer.py,sha256=1r5UPEkUeMCug-P-c1mAZbJPgEXU8hR-fDLdYG5Q-wo,13585
|
131
|
+
sglang/srt/function_call/function_call_parser.py,sha256=IB3QXZjedOFhXcLIOWSiceE_dOqGPcHqqnALu3w-_VY,7682
|
132
|
+
sglang/srt/function_call/llama32_detector.py,sha256=EHYGAy1NCIxFWKdSQByPxyJgFaFRCtGdgj4ntEAgi00,3619
|
133
|
+
sglang/srt/function_call/mistral_detector.py,sha256=xNuVl2vDXVYbXyiXLkJZ9VM6njcwlS9EqryR1eJbMr4,4462
|
134
|
+
sglang/srt/function_call/pythonic_detector.py,sha256=rtXSflE4w993a4OqphWG-WQzvwRz0v3dfgHOnte1fpI,8731
|
135
|
+
sglang/srt/function_call/qwen25_detector.py,sha256=9JfZem_5nw91Og2biwq8eIpUQjy_3kFz4TQI8Lc3Vow,4882
|
121
136
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
122
|
-
sglang/srt/layers/activation.py,sha256=
|
123
|
-
sglang/srt/layers/communicator.py,sha256=
|
124
|
-
sglang/srt/layers/dp_attention.py,sha256=
|
137
|
+
sglang/srt/layers/activation.py,sha256=vJUWe5O72c0yX9jxb0TND_6SFhiOnvHtp9H67ftgYnU,7174
|
138
|
+
sglang/srt/layers/communicator.py,sha256=WbefauUNbwfAtaBySi-rqqXkoFZZpxdOJURLBHpF5qA,18597
|
139
|
+
sglang/srt/layers/dp_attention.py,sha256=e-AgUTa70NsNgsw4hB1a-B_yDv7T8PyXW3jqR8sIKgY,9807
|
125
140
|
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
126
|
-
sglang/srt/layers/layernorm.py,sha256=
|
127
|
-
sglang/srt/layers/linear.py,sha256=
|
128
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
141
|
+
sglang/srt/layers/layernorm.py,sha256=OLjIEv9POyTOOj2G7rSNzIJ6kdA9DM4-azFZALyQhbw,7149
|
142
|
+
sglang/srt/layers/linear.py,sha256=xdAv5qJodLdapHi9ex3e0Qa_KHldcGwEiE-LpLRs1U8,51939
|
143
|
+
sglang/srt/layers/logits_processor.py,sha256=68kkHIwW7mTMSBjUpuw8blLWdL6i3XtHeOcqt4ErYbY,25195
|
129
144
|
sglang/srt/layers/multimodal.py,sha256=YVR69WW-2aGDcZHT8IVJ6F_LRM7wraZr8VjrPDXqDmA,2104
|
130
145
|
sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
|
131
|
-
sglang/srt/layers/pooler.py,sha256=
|
132
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
133
|
-
sglang/srt/layers/rotary_embedding.py,sha256=
|
134
|
-
sglang/srt/layers/sampler.py,sha256=
|
146
|
+
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
147
|
+
sglang/srt/layers/radix_attention.py,sha256=IlqRB4bk06FOH05_7zB8lik0xLpys7jFooLeCwdO0j8,3437
|
148
|
+
sglang/srt/layers/rotary_embedding.py,sha256=D5oj1CwmZ7Dq8I1j0hfKXcd2jn7hzu8Z5eMI7phUDWw,49469
|
149
|
+
sglang/srt/layers/sampler.py,sha256=xNds1migup2s6b9_pS6ljkJUkvNtv7nmTGeIdOzoQ6w,11182
|
135
150
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
136
151
|
sglang/srt/layers/utils.py,sha256=IWGg1Hb7c33Z3LHRPVJyUAzp3BnSid23ZWXAmJ_Jvp8,1204
|
137
152
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=GPKCQiR2yH5Z2XSE9g3vWObdegcwPnMHXv7qEZovLH4,22755
|
138
|
-
sglang/srt/layers/attention/aiter_backend.py,sha256=
|
139
|
-
sglang/srt/layers/attention/base_attn_backend.py,sha256=
|
140
|
-
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=
|
153
|
+
sglang/srt/layers/attention/aiter_backend.py,sha256=7sEUgViw-xl3yok91yyOD9gTi8lQmME0g0ZiKVTCcyI,32851
|
154
|
+
sglang/srt/layers/attention/base_attn_backend.py,sha256=KXVcCguwXh-PSrY9Y2aUrlXXUhWdbVxqVEF2_xIMvm4,3466
|
155
|
+
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=SIR7sKCCegwzahSz82I3gsDyN5TkKoa4yG4-pBQWBi4,9813
|
141
156
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
142
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
143
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
144
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
145
|
-
sglang/srt/layers/attention/flashmla_backend.py,sha256=
|
157
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=JgAp-douu45GYrkxc-d9LHE-rw7pXbVpishHfsU9m_8,92529
|
158
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=Ug4SkZnuHjBBwPOj2TfLlg0eU_GoZvKjhY4oYRU_qqU,49666
|
159
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=NirRlNFxD0S2EncvvmrerIxNfuTnYpvemZV3MR5_FnU,34040
|
160
|
+
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
146
161
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
147
162
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
148
|
-
sglang/srt/layers/attention/tbo_backend.py,sha256=
|
163
|
+
sglang/srt/layers/attention/tbo_backend.py,sha256=xpU8pR_xOwhfWnmAgLL892nb0ujBQWxIbHZAL_d84zI,8175
|
149
164
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzbyKOWHAVPOD9b0n0dEehwlos,9496
|
150
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
165
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=AryrPc4kzioxkiucPkApMA__0HoQTKOHNpwN0GEgm98,36923
|
151
166
|
sglang/srt/layers/attention/utils.py,sha256=KiRSIHaGBhErUhPWCSD3Uiaqb0pSEF0NJFwTTQXoMks,2887
|
152
|
-
sglang/srt/layers/attention/vision.py,sha256
|
153
|
-
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=
|
167
|
+
sglang/srt/layers/attention/vision.py,sha256=-wGBZs9TSY8px-KidPQpEevZiQd577HJ-Wl5cTKQgWM,16291
|
168
|
+
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=eN0Lqpu5h27lMPuRnisX4jrU0WR061pCFSrh3vLlSD0,18936
|
154
169
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
155
170
|
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=ImpCuxszoeVdr6wzaLR3OGW3-50P9EAEvsRCdUVIrxE,14261
|
156
171
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
@@ -160,14 +175,14 @@ sglang/srt/layers/moe/cutlass_moe.py,sha256=--bNTA2BGbHeULb_XXDoRUyWWbE-doHo5K5k
|
|
160
175
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
161
176
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=FIES6H7oS-XjwVsWSrAkQzTdnp7kq-Z5VoViqOHpmtg,4851
|
162
177
|
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
163
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
178
|
+
sglang/srt/layers/moe/topk.py,sha256=fLjl0DZMn6UnUtbx8AjyE0wtAtjn0W64t1DrDXBbjiM,17548
|
164
179
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
165
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
166
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
167
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=
|
180
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=xdYak2dkrUJjmUigKJ-GbWfdf-tXlUKbvtJgxVekbMA,40130
|
181
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=Tl45TYm200db9JNJMuCxgX9yJpKPQ8hUioNkAhUsd7M,52875
|
182
|
+
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=wPc0ewfBeoyYmgKMbp1YoT81OaJSme7AmftrXbxR7Jg,23523
|
168
183
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
169
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
170
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
184
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=FWUfurqSu4NZBzA7oWx2fcqQGtAhPy-U5qgLsaB3lrI,63103
|
185
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=nWmrt8Ihybl3uo0tsDNt0IpyvoBx8QO6KRS4rrP8YL8,29833
|
171
186
|
"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",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
172
187
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
173
188
|
"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",sha256=ouRyZ5PEMPP2njPftCNhs-1g1y6wueWLmhI7G1SjV1k,4131
|
@@ -327,29 +342,29 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=ptJveWp0alXFiwvL6FyXOH5Us
|
|
327
342
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Piw4LN6d8QYrUahWsw3XUOtTMD1o3vHPwA94sGI56Gk,3242
|
328
343
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=3T8_rF2PEojhgTMyQ8DscXgJCWWdWfDPj4M434zWcA4,3243
|
329
344
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
345
|
+
"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",sha256=LNx1W_BsWZcpHomiScCRap46dV0-F7S_w3Htskoqlm8,3263
|
330
346
|
"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",sha256=fo1akCuGoqcGwQgfh56hApgg-wLXfo9kHHksE_6m1F4,3262
|
331
347
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=a9XJZ0XudUTebAdN5guVq-3XSvZetHIRjatO1-_0xCk,3257
|
332
348
|
sglang/srt/layers/quantization/__init__.py,sha256=isMl8LINJFMzEse4r2Ta_7JXT15eKCX4mDIikuwticM,12559
|
333
349
|
sglang/srt/layers/quantization/awq.py,sha256=KemDG55U3B6YZVjMV71awVAIj0islFvtxcUHmOBeGy0,6739
|
334
350
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
335
351
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=vWyPZsRLhdKtSmjvlT5fsowBK_nEebYbDAUh2yqseGw,15285
|
336
|
-
sglang/srt/layers/quantization/
|
337
|
-
sglang/srt/layers/quantization/
|
338
|
-
sglang/srt/layers/quantization/
|
339
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=0Ua9Wt8iWClr9i-M3X-Fk0elA1J8qiRcuapAxxTZVkg,23567
|
352
|
+
sglang/srt/layers/quantization/fp8.py,sha256=Ne3K177lBdWI8TXyJs8qSaH67KaAv2j4LrZeHyqyH_8,44678
|
353
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=pUda_glnAprnFIj3VUgCUYMKb2-uK3UOC3yPahgRMBQ,34743
|
354
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=_90Js9EwurcSKIr69_6avEXbX3--Nd9LicRkRU6CGts,25580
|
340
355
|
sglang/srt/layers/quantization/gptq.py,sha256=d1frUjvXmZfQKkcMQY5t0BA4sXWHE9Jze24qxniptJE,26719
|
341
356
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
342
357
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
343
358
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
344
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
359
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=wW90ZS1ZrGOXf7l5svudmXqAi3JE2SkCV-fwqWeYfdg,30905
|
345
360
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=PBgcQULe9oD2i96BeJRZtIdIUkWzS0IWU9ev3C-h7mw,19646
|
346
361
|
sglang/srt/layers/quantization/qoq.py,sha256=adhsCixRUTh1m8sfpRWNhh5oX3I1WJli3Elg8uexP6A,8222
|
347
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
362
|
+
sglang/srt/layers/quantization/utils.py,sha256=qHdWbLQD8teKhv2tOcuyGegpFonXygoJHwCAD7Ur5MA,5439
|
348
363
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=ZB6ydquyPOORDe9OCoEBRH6dsQhCeRWv1YIgm8UDQwQ,11622
|
349
364
|
sglang/srt/layers/quantization/w8a8_int8.py,sha256=_BG6Zo4tis0UGZ47EVfBmfpOxRKzXvd3EM15qDWy7OM,9147
|
350
365
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
351
366
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EaOKuIA0zXwqmH_eVhWeNdGJT9d1d9gVvFyYkgpdjDg,25665
|
352
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
367
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=w19mhCnOre3j6L2-Tc_sRtBPgwBOAKV4QmYLpzyU_Fk,26637
|
353
368
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
354
369
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
355
370
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
@@ -507,12 +522,16 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
507
522
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
508
523
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=FImA-TJ_tQDjqwoNWxS--sRDoKDXf9gamlME3tkxH58,3252
|
509
524
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FFBjSWlpKXMxfAUUYUqXbOK_Hd7qBeBsfbcaa9uB4qY,3249
|
525
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
526
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=BrzCCxXtJJHXMmKlo9nm711ZB-yO4uGw4PJLdnY_qqw,11527
|
527
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=zkMzBAqQTSwG9TlGPuwmHV1yN0v5Y_5Hgyo0CKQDVNU,741
|
528
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=On_uvP1ThxgQFAzOWKoteM0vIOHqmtI127A4qbPtmbc,3264
|
510
529
|
sglang/srt/lora/layers.py,sha256=FaTYf0w3zbKKKAT1nJdAzGRtxvySB6FpNKXvEi5RHH0,12958
|
511
530
|
sglang/srt/lora/lora.py,sha256=WY3cISWrQ5Ye3YcNKJUwAWRImzlpLQva2fGepg6P5EY,9744
|
512
531
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
513
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
514
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
515
|
-
sglang/srt/lora/utils.py,sha256=
|
532
|
+
sglang/srt/lora/lora_manager.py,sha256=pXQuS30X1KaqzDk1bD6Cb-cClcGopJcoNvGpXMshe54,18316
|
533
|
+
sglang/srt/lora/mem_pool.py,sha256=M4l4RO4tRjii5T4fq89nUoKJNHusaQHwvLrkryBCb1U,10132
|
534
|
+
sglang/srt/lora/utils.py,sha256=f3eySsA2tqlzMkvqwtRPWKIRjDiMk6ZFh9CJfUYdeqI,5486
|
516
535
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
517
536
|
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
518
537
|
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
@@ -521,7 +540,7 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=vOUDzC_Sq7UGnDbdF8F7ChKG12hD
|
|
521
540
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=qCpJAksCSXS3Znm-ABx1QfrdNqj9hrP61oaeW-n2RhU,5945
|
522
541
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=yNBgl8jS76DPlGJg8puRkSnKkewf2_2oKfVZZRq4lYY,4351
|
523
542
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=EoF9HymgQ1V9DwyOJOvbw1hCbEjprVOne_fC4VHgj-s,4518
|
524
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
543
|
+
sglang/srt/managers/cache_controller.py,sha256=K00t5dSZU6gbAMHZWhNyj0ndgHISvelTl7UMI5KqBuE,19352
|
525
544
|
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
526
545
|
sglang/srt/managers/data_parallel_controller.py,sha256=PZ-wOcAFn3PQqMB6I2vjIsFmplf0nlNl5hqTDKTHTG8,12112
|
527
546
|
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
@@ -529,22 +548,23 @@ sglang/srt/managers/eplb_manager.py,sha256=YaxnvD1-wMV7BhtF9AxoNRVsJUdlQzFF7N-JD
|
|
529
548
|
sglang/srt/managers/expert_distribution.py,sha256=HBcfNdS3l6ob17Z9KFlX5f79rqcaY41XMDp8emMD-TY,30880
|
530
549
|
sglang/srt/managers/expert_location.py,sha256=ZSsH17k5bAgbE1wuvpGaHGueiyhfPrgQakBFPu9jswo,16669
|
531
550
|
sglang/srt/managers/expert_location_dispatch.py,sha256=U6-XLZ77RK0oy_JUVug2q-2LJjwoYX-js0_zhBNMXuM,4148
|
532
|
-
sglang/srt/managers/io_struct.py,sha256=
|
551
|
+
sglang/srt/managers/io_struct.py,sha256=bWybydmTbTuKW_AO6VjHPhB5jbWFdA7qcxb5Ee7Txkg,33687
|
533
552
|
sglang/srt/managers/mm_utils.py,sha256=mA9W4xZBnXfs-4ZeALvhdpGAYxrJGfOxBWyoHVrt44Q,26518
|
534
553
|
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
535
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
536
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
537
|
-
sglang/srt/managers/scheduler.py,sha256=
|
554
|
+
sglang/srt/managers/schedule_batch.py,sha256=meRGsHztVoSWNHuyq-Qzb_0Xk88d4OasGTvTYBvKoI8,72781
|
555
|
+
sglang/srt/managers/schedule_policy.py,sha256=0T8URzQmLvEmG-42-SFBBl9WnsOSwYO8-_CcBpuD38M,20474
|
556
|
+
sglang/srt/managers/scheduler.py,sha256=FcnzE0JuheAvuZlslbZRF7sQIbRIcwMkKKHp6--mGxs,108539
|
538
557
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=aaj0z1PD3fGIOPoTtWwqoKsii0yQCR7txVFXMPECveQ,29879
|
539
558
|
sglang/srt/managers/session_controller.py,sha256=Lh1kruMcKqR7WVWYJRZbYgowtsssVlP7_paIVXLLIcE,5756
|
540
|
-
sglang/srt/managers/
|
541
|
-
sglang/srt/managers/
|
542
|
-
sglang/srt/managers/
|
559
|
+
sglang/srt/managers/template_manager.py,sha256=RrwRA2oqId_PMQ98qJQGwIxMroOxiorl2sGC9ARou_0,8543
|
560
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=zZR4c-jCm0n8LBn_5PT5eSv8Jptt50HM7OQeCvxBVqk,65586
|
561
|
+
sglang/srt/managers/tp_worker.py,sha256=A010h6fHS4gjsaqymQyAFiqLnZGUZiTi9rHIr3blmk0,10436
|
562
|
+
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=jB9W7qSXKKnBrTep1yNKrYgLlylJvL-ab2Sa1ki6f0s,10349
|
543
563
|
sglang/srt/managers/utils.py,sha256=9_VGE48EK0PXVJ26aYvbRJ6n7gIZALvCcf6uZCccCgM,1369
|
544
564
|
sglang/srt/managers/eplb_algorithms/__init__.py,sha256=wVUv2ZhhC-_VbLaStpk3vulzhqExwfHGZJQqoohs-Fw,1963
|
545
565
|
sglang/srt/managers/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9enSt426uUTKeiq4,8340
|
546
566
|
sglang/srt/managers/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
547
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256
|
567
|
+
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=DQk5qNh7MDY9DQoASiQbCTwRb2HdvLWobzHmE0Ni_fg,21500
|
548
568
|
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
549
569
|
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=CMfhhdq7u6GzT8ZENo7ByClvQEx-HKaTGVgdYM1vMNw,3460
|
550
570
|
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=oBHXlbwto_84ZkjkW2A7F3Z7kNuDf039uDH4HVXKE1s,2290
|
@@ -558,34 +578,36 @@ sglang/srt/managers/multimodal_processors/mllama4.py,sha256=IAu09ZPMAHxZKsfGiKjZ
|
|
558
578
|
sglang/srt/managers/multimodal_processors/phi4mm.py,sha256=-yTlt2kQkrgks2IzaRKmEj-7siAvTDhZHDR_J3NVFdw,2610
|
559
579
|
sglang/srt/managers/multimodal_processors/pixtral.py,sha256=uQJYbxhafNCmg0xP52FdElnkUatAyintER1XNuKz3b8,4195
|
560
580
|
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=RLv8sBuKhAjeaVqrFR7hwEEw7fX1WOMZ6r2R4gFeV04,7025
|
561
|
-
sglang/srt/
|
562
|
-
sglang/srt/mem_cache/
|
581
|
+
sglang/srt/managers/multimodal_processors/vila.py,sha256=AeQlhdIKKoN0lre8_zYQ7YpGu7I_rux1bRLt70sPKJ0,2594
|
582
|
+
sglang/srt/mem_cache/allocator.py,sha256=gujYY5DFYQIz8VDAUOjATKtxUMpdRo6xkBunPF08SG4,12526
|
583
|
+
sglang/srt/mem_cache/base_prefix_cache.py,sha256=XHSzXKgBin-m1HsL47K-GobhLnajaGxqLqGtrLsWaZ0,2540
|
584
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=580NlAzr9Pm4yjvX5S_QP9ify998oOEPQuMpRye7uW8,2005
|
563
585
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
564
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
565
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
586
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=Z_XgbLBxI8SN7kgsi1R6iX6AfgDUF5-ynVnBVRF7KUw,17061
|
587
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=yLYDZ7-rLQi-nkhC_KuT4YmxnEOqM6Rq-j4_HAPehh4,27583
|
588
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=9N34Y7P0aM2xkmhsEw2_W8xN897h-HEwzRPIu1REwac,13186
|
566
589
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=Q-lYcI-3HoLu0WJhE2F_An8g9mkZ8LwMrYnQ4383Rf0,1266
|
567
|
-
sglang/srt/mem_cache/
|
568
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=foS7mmPCCUWDP12aQCZGw7XAJqYfzZTowkoCTOa7jjY,16656
|
590
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=ojr9_bUwnPocmpbGZXz8JKac4dS-PrfNYk8UqF4Gvi8,17936
|
569
591
|
sglang/srt/metrics/collector.py,sha256=C9QEJDOEdOPBwy2IJwFS3R6VbGzVzGs2xakKCCPvQDk,19903
|
570
592
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
571
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
593
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=OqU5EYdJU6pfk3fMNPklnvVhlMaXKWWKguLkAV9cdbw,30444
|
572
594
|
sglang/srt/model_executor/expert_location_updater.py,sha256=HWLY5lJAWefy2tobWJKlHs3qlBSCS57EwSMdfUuPFc4,20585
|
573
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
574
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
595
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=ueHsjmGm52YqVK-8f-TRYpERCCdeSBuc2yaqxD9pWkQ,29268
|
596
|
+
sglang/srt/model_executor/model_runner.py,sha256=mbYBcddyYxBuRcFmRawa17xdxySxdG-LwxmovH4BCLw,54309
|
575
597
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
576
|
-
sglang/srt/model_loader/loader.py,sha256=
|
598
|
+
sglang/srt/model_loader/loader.py,sha256=R1-_cWKvrFx6zWWDYxKHOnfP7QtnVmMXi_zyS6seeCI,56286
|
577
599
|
sglang/srt/model_loader/utils.py,sha256=zSZBPA9ErPmkf-HfCxJjhmiFwYueB15KUg7NFspLvPY,4454
|
578
|
-
sglang/srt/model_loader/weight_utils.py,sha256=
|
600
|
+
sglang/srt/model_loader/weight_utils.py,sha256=XwNVS5MLtNzW5fTS5UDK2CHUuSDMHKznI4Du8l4xoks,32562
|
579
601
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
580
|
-
sglang/srt/models/bert.py,sha256=
|
602
|
+
sglang/srt/models/bert.py,sha256=ODJe8YfNRP-hHsomFWk4_QpcuiSsNfjzGf256EDS0Pc,15802
|
581
603
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
582
604
|
sglang/srt/models/clip.py,sha256=mkdSNhc2SgRHyeq9tCLEjUGdnA8yS2EMMbMKSpn5dMs,19863
|
583
605
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
584
606
|
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
585
607
|
sglang/srt/models/deepseek.py,sha256=ZnN02HdgXCB23Vno5V9UMUoOxH5HC82vNTwsVulUJ-o,17206
|
586
608
|
sglang/srt/models/deepseek_janus_pro.py,sha256=OeeI7vZbE4HGpxa8CwT6-Lbfs7J7WMQ3oBNpVJQpv3w,70450
|
587
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
588
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
609
|
+
sglang/srt/models/deepseek_nextn.py,sha256=LaNBVtTSSO6_v5VRq-aZQ7K7lVFSIlUm8NcBB9p0fmw,5751
|
610
|
+
sglang/srt/models/deepseek_v2.py,sha256=8sYA5m2a590tF58IvRzOnPQUshKFAhQxQCbRmqEzoyY,89180
|
589
611
|
sglang/srt/models/deepseek_vl2.py,sha256=j8BdxZsMjm6lPdbDipEIKhVIVywCP1Vl1Kl46BZ5_0Y,13147
|
590
612
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
591
613
|
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
@@ -593,6 +615,7 @@ sglang/srt/models/gemma2.py,sha256=kqtwdo93GWKm2iBN29RoIRH2ggRm-K_80LM5btgfBLo,1
|
|
593
615
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
594
616
|
sglang/srt/models/gemma3_causal.py,sha256=Vm605KeF7CBXbtxzOWF-v0TLbl0G12CLF-bEgTV9T0E,25197
|
595
617
|
sglang/srt/models/gemma3_mm.py,sha256=b9YmkipsfVb5IXVeIVwW_PviXiCkRULhEsqNOvPoDxU,17221
|
618
|
+
sglang/srt/models/glm4.py,sha256=2VQzUqFkQTy_2nfkxP9SF6_9kKLTZUExGRjge7r99Es,11265
|
596
619
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
597
620
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
598
621
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
@@ -600,7 +623,7 @@ sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,280
|
|
600
623
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
601
624
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
602
625
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
603
|
-
sglang/srt/models/internvl.py,sha256=
|
626
|
+
sglang/srt/models/internvl.py,sha256=fZ18eKFYvvtYqoBRXKmS7KlgHMewJSAykADnrf0N3nk,23267
|
604
627
|
sglang/srt/models/kimi_vl.py,sha256=rMJezfEYaEjOaMZ7vt0rg9ZlbV9p1Ax6-kDsVWzf_bI,12868
|
605
628
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
606
629
|
sglang/srt/models/llama.py,sha256=qLBfL77XG3pI-UDxg5HLcgJN1tUMeWNj9-AUR4fUVGg,27144
|
@@ -613,7 +636,7 @@ sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZe
|
|
613
636
|
sglang/srt/models/llava.py,sha256=m0-qcEWEUyN7kIiCYJAZTi58MwL4ioqCAD99PSTpsuY,37496
|
614
637
|
sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc,12829
|
615
638
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
616
|
-
sglang/srt/models/mimo_mtp.py,sha256=
|
639
|
+
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
617
640
|
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
618
641
|
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
619
642
|
sglang/srt/models/minicpmo.py,sha256=IBMFTmak4qokNl8zBXHLYfS5slPf88ECwox6CKHbiAU,76081
|
@@ -640,36 +663,34 @@ sglang/srt/models/qwen2_vl.py,sha256=A6YGktXkc9rvotLo0KcZpoUP60eUcFzoiDG65UzXZeI
|
|
640
663
|
sglang/srt/models/qwen3.py,sha256=L-m441pSsduaayMzILrN3isnNqK7jVraUmm_6bEJb1M,14989
|
641
664
|
sglang/srt/models/qwen3_moe.py,sha256=2nOngjhOw93m6nNx0Rc3fM0Yh5lBz_GM1Ri-FCRB-s4,30824
|
642
665
|
sglang/srt/models/registry.py,sha256=bH9H0OiNV0Cn7FRBM30Oh6dxICTs9mJscdLtHYPJvxc,3783
|
643
|
-
sglang/srt/models/roberta.py,sha256=
|
666
|
+
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
644
667
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
645
668
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
646
669
|
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
647
670
|
sglang/srt/models/transformers.py,sha256=_CL0npi-_HvqzxkLgFhv2EE3bfGvCLXPYAtPFywZOr0,10260
|
671
|
+
sglang/srt/models/vila.py,sha256=DRGJXP6iSv0XjgHYIJpMzBDNYZb3__Gg_wFkmZ5D66Y,9865
|
648
672
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
649
673
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
650
674
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
651
|
-
sglang/srt/openai_api/adapter.py,sha256=dAJ6JAnBNQHCtSx6n2iwHl5Fmv3eA-5umg0cE5pZkxw,80511
|
652
|
-
sglang/srt/openai_api/protocol.py,sha256=ViynhRhAX0CknesQNtwXwR8_BhLsjRdAi-To08JpRhs,15312
|
653
|
-
sglang/srt/openai_api/utils.py,sha256=LL8VB-Qv9kNIVVWG1PYzoKMMHo7Y2NeVLMeJ9QEWVk8,6600
|
654
675
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
655
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
656
|
-
sglang/srt/sampling/sampling_params.py,sha256=
|
676
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=JOGU-Fa8wPtytEJ30BHg1PldeNytwy8u31azLH436kw,13450
|
677
|
+
sglang/srt/sampling/sampling_params.py,sha256=L2cU3MhAo9OvfdEtTdJidp9nTOkD6tiwlegxQ5vgIfU,6127
|
657
678
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
658
679
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
659
680
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
660
681
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
661
682
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
662
|
-
sglang/srt/speculative/build_eagle_tree.py,sha256=
|
663
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
664
|
-
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=
|
665
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
666
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
683
|
+
sglang/srt/speculative/build_eagle_tree.py,sha256=lxfaTEOTY0N9QTlgXSUae3DVtPLqW8CcYXWcHsxCJp4,11632
|
684
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=fSNaHYJOQUgy2_AHRlZPYSQRIMgSiL_Pz5h53eothx4,14239
|
685
|
+
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=sdIHbcWwgsXDoo64-T5veDuYB5eHC9QBwu2Ns29SCSI,14930
|
686
|
+
sglang/srt/speculative/eagle_utils.py,sha256=cBQYqryCr4is5E_16xIcUue0Q2_Mn4meY8NCyuu4RAg,45558
|
687
|
+
sglang/srt/speculative/eagle_worker.py,sha256=fjYJmzz8vYCf3xod0dYoGmwyFWh6iTjnGfbV6SdY32M,38105
|
667
688
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
668
689
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
669
690
|
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
670
691
|
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
671
692
|
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
672
|
-
sglang/test/runners.py,sha256=
|
693
|
+
sglang/test/runners.py,sha256=AOnCXNGO9AYWrUShCDoxYajiN5yVFF9b8fT6XnwAWew,32439
|
673
694
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
674
695
|
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
675
696
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
@@ -678,8 +699,9 @@ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWU
|
|
678
699
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
679
700
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
680
701
|
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
681
|
-
sglang/test/test_block_fp8.py,sha256=
|
682
|
-
sglang/test/
|
702
|
+
sglang/test/test_block_fp8.py,sha256=1qBD-FJr5UaR9e5qDz91vDrS_DT1utnk82qeQ2bm-1E,21630
|
703
|
+
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
704
|
+
sglang/test/test_block_fp8_ep.py,sha256=Ufq6p32sb1RSbFKaSnsVF8RrqqwwAACBUgOJTEH2Lbc,10856
|
683
705
|
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
684
706
|
sglang/test/test_cutlass_moe.py,sha256=beXdvpwpHh0O8fpLW-RV3Bx8Wu0lRFG_SNkL3Op5ITA,9905
|
685
707
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
@@ -687,13 +709,13 @@ sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsu
|
|
687
709
|
sglang/test/test_fp4_moe.py,sha256=U4LHzpGl6pCiCZiENRPxVP6hxqkqRZ_0WXbB29vYeAo,8187
|
688
710
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
689
711
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
690
|
-
sglang/test/test_utils.py,sha256=
|
712
|
+
sglang/test/test_utils.py,sha256=UfVq6snSqzomW0sDTql54Vbefl6kVovbFx1R79y_mqw,36243
|
691
713
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
692
714
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
693
715
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
694
|
-
sglang/test/attention/test_prefix_chunk_info.py,sha256=
|
695
|
-
sglang-0.4.
|
696
|
-
sglang-0.4.
|
697
|
-
sglang-0.4.
|
698
|
-
sglang-0.4.
|
699
|
-
sglang-0.4.
|
716
|
+
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
717
|
+
sglang-0.4.8.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
718
|
+
sglang-0.4.8.dist-info/METADATA,sha256=8Spz4kOLcrEbQuzVTiI4EE0A4Ldrdcholyuz3mNVUC4,26603
|
719
|
+
sglang-0.4.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
720
|
+
sglang-0.4.8.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
721
|
+
sglang-0.4.8.dist-info/RECORD,,
|