sglang 0.5.1.post2__py3-none-any.whl → 0.5.2rc0__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_one_batch.py +3 -0
- sglang/bench_one_batch_server.py +79 -53
- sglang/bench_serving.py +186 -14
- sglang/profiler.py +0 -1
- sglang/srt/configs/__init__.py +2 -0
- sglang/srt/configs/longcat_flash.py +104 -0
- sglang/srt/configs/model_config.py +12 -0
- sglang/srt/connector/__init__.py +1 -1
- sglang/srt/connector/base_connector.py +1 -2
- sglang/srt/connector/redis.py +2 -2
- sglang/srt/connector/serde/__init__.py +1 -1
- sglang/srt/connector/serde/safe_serde.py +4 -3
- sglang/srt/conversation.py +38 -5
- sglang/srt/disaggregation/ascend/conn.py +75 -0
- sglang/srt/disaggregation/launch_lb.py +0 -13
- sglang/srt/disaggregation/mini_lb.py +33 -8
- sglang/srt/disaggregation/prefill.py +1 -1
- sglang/srt/distributed/parallel_state.py +24 -14
- sglang/srt/entrypoints/engine.py +19 -12
- sglang/srt/entrypoints/http_server.py +174 -34
- sglang/srt/entrypoints/openai/protocol.py +87 -24
- sglang/srt/entrypoints/openai/serving_chat.py +50 -9
- sglang/srt/entrypoints/openai/serving_completions.py +15 -0
- sglang/srt/eplb/eplb_manager.py +26 -2
- sglang/srt/eplb/expert_distribution.py +29 -2
- sglang/srt/function_call/deepseekv31_detector.py +222 -0
- sglang/srt/function_call/function_call_parser.py +2 -0
- sglang/srt/function_call/gpt_oss_detector.py +144 -256
- sglang/srt/harmony_parser.py +588 -0
- sglang/srt/hf_transformers_utils.py +26 -7
- sglang/srt/layers/activation.py +12 -0
- sglang/srt/layers/attention/ascend_backend.py +374 -136
- sglang/srt/layers/attention/flashattention_backend.py +241 -7
- sglang/srt/layers/attention/flashinfer_backend.py +5 -2
- sglang/srt/layers/attention/flashinfer_mla_backend.py +5 -2
- sglang/srt/layers/attention/hybrid_attn_backend.py +53 -21
- sglang/srt/layers/attention/trtllm_mla_backend.py +25 -10
- sglang/srt/layers/communicator.py +1 -2
- sglang/srt/layers/layernorm.py +28 -3
- sglang/srt/layers/linear.py +3 -2
- sglang/srt/layers/logits_processor.py +1 -1
- sglang/srt/layers/moe/cutlass_moe.py +0 -8
- sglang/srt/layers/moe/ep_moe/kernels.py +74 -0
- sglang/srt/layers/moe/ep_moe/layer.py +13 -13
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=64,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- sglang/srt/layers/moe/topk.py +35 -12
- sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py +133 -235
- sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +5 -10
- sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py +5 -23
- sglang/srt/layers/quantization/fp8.py +2 -1
- sglang/srt/layers/quantization/fp8_kernel.py +2 -2
- sglang/srt/layers/quantization/fp8_utils.py +2 -2
- sglang/srt/layers/quantization/modelopt_quant.py +7 -0
- sglang/srt/layers/quantization/mxfp4.py +25 -27
- sglang/srt/layers/quantization/mxfp4_tensor.py +3 -1
- sglang/srt/layers/quantization/utils.py +13 -0
- sglang/srt/layers/quantization/w8a8_int8.py +7 -3
- sglang/srt/layers/rotary_embedding.py +28 -1
- sglang/srt/layers/sampler.py +29 -5
- sglang/srt/layers/utils.py +0 -14
- sglang/srt/managers/cache_controller.py +237 -204
- sglang/srt/managers/detokenizer_manager.py +48 -2
- sglang/srt/managers/io_struct.py +57 -0
- sglang/srt/managers/mm_utils.py +5 -1
- sglang/srt/managers/multi_tokenizer_mixin.py +591 -0
- sglang/srt/managers/scheduler.py +94 -9
- sglang/srt/managers/scheduler_output_processor_mixin.py +20 -18
- sglang/srt/managers/scheduler_update_weights_mixin.py +8 -1
- sglang/srt/managers/tokenizer_manager.py +122 -42
- sglang/srt/mem_cache/chunk_cache.py +1 -1
- sglang/srt/mem_cache/hicache_storage.py +51 -23
- sglang/srt/mem_cache/hiradix_cache.py +87 -71
- sglang/srt/mem_cache/lora_radix_cache.py +1 -1
- sglang/srt/mem_cache/memory_pool.py +77 -14
- sglang/srt/mem_cache/memory_pool_host.py +4 -5
- sglang/srt/mem_cache/radix_cache.py +6 -4
- sglang/srt/mem_cache/radix_cache_cpp.py +1 -1
- sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +38 -20
- sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py +87 -82
- sglang/srt/mem_cache/swa_radix_cache.py +1 -1
- sglang/srt/model_executor/model_runner.py +6 -5
- sglang/srt/model_loader/loader.py +15 -24
- sglang/srt/model_loader/utils.py +12 -0
- sglang/srt/models/deepseek_v2.py +38 -13
- sglang/srt/models/gpt_oss.py +2 -15
- sglang/srt/models/llama_eagle3.py +4 -0
- sglang/srt/models/longcat_flash.py +1015 -0
- sglang/srt/models/longcat_flash_nextn.py +691 -0
- sglang/srt/models/qwen2.py +26 -3
- sglang/srt/models/qwen2_5_vl.py +66 -41
- sglang/srt/models/qwen2_moe.py +22 -2
- sglang/srt/models/transformers.py +1 -1
- sglang/srt/multimodal/processors/base_processor.py +4 -2
- sglang/srt/reasoning_parser.py +56 -300
- sglang/srt/sampling/penaltylib/orchestrator.py +14 -2
- sglang/srt/server_args.py +122 -56
- sglang/srt/speculative/eagle_worker.py +28 -8
- sglang/srt/tokenizer/tiktoken_tokenizer.py +6 -1
- sglang/srt/utils.py +73 -5
- sglang/test/attention/test_trtllm_mla_backend.py +12 -3
- sglang/version.py +1 -1
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2rc0.dist-info}/METADATA +7 -6
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2rc0.dist-info}/RECORD +107 -99
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2rc0.dist-info}/WHEEL +0 -0
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2rc0.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.5.1.post2.dist-info → sglang-0.5.2rc0.dist-info}/top_level.txt +0 -0
@@ -1,15 +1,15 @@
|
|
1
1
|
sglang/__init__.py,sha256=CK60u1J439CJZaPihWqlDjFZ8doIC-5YgIYz-E1PIh4,1823
|
2
2
|
sglang/bench_offline_throughput.py,sha256=Bge0KG4Uiv9CHsxDnqKdXJmG_TcxM4blz3CmvLmDRvM,14815
|
3
|
-
sglang/bench_one_batch.py,sha256=
|
4
|
-
sglang/bench_one_batch_server.py,sha256=
|
5
|
-
sglang/bench_serving.py,sha256=
|
3
|
+
sglang/bench_one_batch.py,sha256=ITGCBFPksSyoXPEgAqZruGY2ZUPyOoc111jf1nil0go,23137
|
4
|
+
sglang/bench_one_batch_server.py,sha256=d-XnTgyUzsEeOHyuc-DGZDeW4ZB4V59aV9Ojr3H43SE,14676
|
5
|
+
sglang/bench_serving.py,sha256=TcT-yEO9bJW4VASIrfJaDZwKepBcerBUmVPeKbWoruI,78205
|
6
6
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
7
7
|
sglang/compile_deep_gemm.py,sha256=EsgboGA-MK3Rvx9TlUJPLxJ5LBira4bTcHJLKEp1H6k,6488
|
8
8
|
sglang/global_config.py,sha256=ZMTux_PsGnvkyJ0kTFwhTdbnFwIjjpGDogut_9Lu4Vo,1732
|
9
9
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
10
|
-
sglang/profiler.py,sha256=
|
10
|
+
sglang/profiler.py,sha256=JCpZzlDhahoiPlPi5IG3n7GFrQHxfHEB6ELie3Ck55w,4397
|
11
11
|
sglang/utils.py,sha256=dC2PNkKYTgDHsNrWdZJ74GvaXGSHCeIk_aZ-TA89OhY,16380
|
12
|
-
sglang/version.py,sha256=
|
12
|
+
sglang/version.py,sha256=wVQ3e58PHT2hhCLFcOLsyR4-dgdre7yd49m4mJK4CO8,25
|
13
13
|
sglang/eval/llama3_eval.py,sha256=mLNRZJIqV4CfqrY8UGnJEcHw2Xsyr1eyYZgFSUFYr1g,9997
|
14
14
|
sglang/eval/loogle_eval.py,sha256=-CC2s2kh5qUoDrHRkQVkC_jNvBgNojXbf456ny5s78s,4557
|
15
15
|
sglang/lang/api.py,sha256=rcp3GeoyZhmJ0GDLPRkuZNcxd0TBJy_wfUDpcmQoqW8,7210
|
@@ -30,9 +30,10 @@ sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
|
30
30
|
sglang/srt/bench_utils.py,sha256=zNTsTBUta27XxojgvR5p5X9M0v1MFzZ7dcX9TMq4NvQ,4348
|
31
31
|
sglang/srt/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
32
32
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
33
|
-
sglang/srt/conversation.py,sha256=
|
33
|
+
sglang/srt/conversation.py,sha256=cmVT4SCqRYxprYvmftUC_z_TkhXCqYC9B2rVZsmQe30,38869
|
34
34
|
sglang/srt/custom_op.py,sha256=7OPQAZe3PqDXk-xM0Wxl7pm9cazilNJfkNiYIWztWgI,3198
|
35
|
-
sglang/srt/
|
35
|
+
sglang/srt/harmony_parser.py,sha256=YweG4azWm5jmzYGaAHEXSaORpgWctPpSGQk_jp5H-CE,23227
|
36
|
+
sglang/srt/hf_transformers_utils.py,sha256=XifKc8JTPr_CkQtdLZ5-OvsNzapGgny_JJSIkYaiJYo,15674
|
36
37
|
sglang/srt/host_shared_memory.py,sha256=00TgVm3PNCl4rTPJZChG5uu4I5hd_Xf587r39tibmIg,2274
|
37
38
|
sglang/srt/jinja_template_utils.py,sha256=XCuqi6iHQrtziUvhy22ePdh8WcS42O9sKxuXpM_bMXc,7836
|
38
39
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
@@ -41,13 +42,13 @@ sglang/srt/operations.py,sha256=za_h1_kcR1Te6-i_r0i_zAeumbmIRhLK2pS31sukkrw,6089
|
|
41
42
|
sglang/srt/operations_strategy.py,sha256=-w6GI2VgSGvORy3pUWRAJo6244ykSW1ZBV1Dx0fZlHA,7138
|
42
43
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
43
44
|
sglang/srt/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
44
|
-
sglang/srt/reasoning_parser.py,sha256=
|
45
|
-
sglang/srt/server_args.py,sha256=
|
45
|
+
sglang/srt/reasoning_parser.py,sha256=HEWAeFzPA_Jn3a44BYCz61QNV6kAvX46Y0tR8csAUg4,11152
|
46
|
+
sglang/srt/server_args.py,sha256=qEh8ykOglDMHh3GvyUhG0oOSJq_tH8vUYtDzSukoOtk,104043
|
46
47
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
47
48
|
sglang/srt/two_batch_overlap.py,sha256=UykF5nC2rja3Hvmu0D9glqKdVRIEhQGPV84Jm7veopQ,34150
|
48
|
-
sglang/srt/utils.py,sha256=
|
49
|
+
sglang/srt/utils.py,sha256=K0GxDnxVKs5LeqbCiphtGpGd5w4kPzzQsqgHkT1e0Ic,95522
|
49
50
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
50
|
-
sglang/srt/configs/__init__.py,sha256=
|
51
|
+
sglang/srt/configs/__init__.py,sha256=3GdmJ2DUiNq1zNs3yOILwZzL0J8fK-h8k2P5YVgxEI0,833
|
51
52
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
52
53
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
53
54
|
sglang/srt/configs/deepseekvl2.py,sha256=sYMmoy5_LlDXht7MTi4QGYOaiE8iMGUO44bnuOu4i8I,23683
|
@@ -58,17 +59,18 @@ sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsr
|
|
58
59
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
59
60
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
60
61
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
61
|
-
sglang/srt/configs/
|
62
|
+
sglang/srt/configs/longcat_flash.py,sha256=Qp25xJVLq2K72Z80cXhcJxtqhagAdiPySDoevuT0Sno,3589
|
63
|
+
sglang/srt/configs/model_config.py,sha256=n28KH8pqOqQNyyOwvYEXpkDZ1z8tzPe1sfV4dGmPrHc,31607
|
62
64
|
sglang/srt/configs/step3_vl.py,sha256=_Otgnym57DVgB_kZ__8c1_Ys5gSalA_K0ZuVjcG51T0,4845
|
63
65
|
sglang/srt/configs/update_config.py,sha256=GEf-XhL8JPrbX9-Hz8V7S3M6YTg76DVdIhc_4YdMDtc,6291
|
64
66
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
65
|
-
sglang/srt/connector/__init__.py,sha256=
|
66
|
-
sglang/srt/connector/base_connector.py,sha256=
|
67
|
-
sglang/srt/connector/redis.py,sha256=
|
67
|
+
sglang/srt/connector/__init__.py,sha256=7sKpAYPdW9NC0A3sbUmDVgLuMf9b2jwifnVMs2Q7Ow4,1243
|
68
|
+
sglang/srt/connector/base_connector.py,sha256=LCKsTX_yWHclPrzNNB1fLwVCN8rIDKZaZhqHQ54B9MU,2774
|
69
|
+
sglang/srt/connector/redis.py,sha256=K3fJSm2rZsd0R_KkICV3jIWKtrwxXE1tYktWnovLbz4,2514
|
68
70
|
sglang/srt/connector/s3.py,sha256=hn5Ow9Y6ItS8RMJDwnTQe5QaiQ7HKMgiwggE9QnUewM,3743
|
69
71
|
sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8,983
|
70
|
-
sglang/srt/connector/serde/__init__.py,sha256=
|
71
|
-
sglang/srt/connector/serde/safe_serde.py,sha256=
|
72
|
+
sglang/srt/connector/serde/__init__.py,sha256=zuleyYN-jrDyiPiXjTbQKA27llb4H7HuDTZcBwrLk1U,707
|
73
|
+
sglang/srt/connector/serde/safe_serde.py,sha256=XSjb9mRv1HqeG6Jiw633EOQYlrcI23Q21UluYqPZaWA,760
|
72
74
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
73
75
|
sglang/srt/constrained/base_grammar_backend.py,sha256=ATWX1LKp3GjUDVkauEaSc3MnS8Bt6hOiHUgeYDZtgNo,7059
|
74
76
|
sglang/srt/constrained/llguidance_backend.py,sha256=Au8G8x4EB39w7k9-GFLP2hOPETyeAPw53RRZYdLimpA,6191
|
@@ -84,12 +86,12 @@ sglang/srt/debug_utils/text_comparator.py,sha256=pg58q3fzsnd3rJKRgZTdcOviOtAv8pS
|
|
84
86
|
sglang/srt/disaggregation/decode.py,sha256=EELA3krHp4YtRIpUYU0-9LSFd7XQuvKn3yiHGrK7gaI,34598
|
85
87
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=Iu7ehHGAfYIVATtClwX6y-6zxWs-JyDlMotYo_5yuUc,6598
|
86
88
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
87
|
-
sglang/srt/disaggregation/launch_lb.py,sha256=
|
88
|
-
sglang/srt/disaggregation/mini_lb.py,sha256=
|
89
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
89
|
+
sglang/srt/disaggregation/launch_lb.py,sha256=x355ULx1tUOkSSDae5INMQoG8sPC-l-hMh4FBk9MAaI,3439
|
90
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=pZ4MYR0DE_DJpINTcckbJTBdz8Y9NAOjOqPqbHPThJo,15599
|
91
|
+
sglang/srt/disaggregation/prefill.py,sha256=gf8ju_REf5FxPg_QtmlMEipeo1N5muUcZHRkaKtfMhY,36286
|
90
92
|
sglang/srt/disaggregation/utils.py,sha256=evdv4AkQxJzTqdO0jrdAr7vHUbBSCEXMzNREh0FoRLc,12294
|
91
93
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
92
|
-
sglang/srt/disaggregation/ascend/conn.py,sha256=
|
94
|
+
sglang/srt/disaggregation/ascend/conn.py,sha256=EuCsFMxwxDp7jt8K2uyTtRlIk0Vi5A_VBz6hKYwybhU,4119
|
93
95
|
sglang/srt/disaggregation/ascend/transfer_engine.py,sha256=_4PszsQL6wICdg5cqpR2N9TbZpUY6bBX8tgE3xeaYfc,2137
|
94
96
|
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
95
97
|
sglang/srt/disaggregation/base/conn.py,sha256=xQ-UB_brdn9vHr-NSbzuR6BysDPGh0Pt9h836iUgbX8,2901
|
@@ -106,7 +108,7 @@ sglang/srt/disaggregation/nixl/conn.py,sha256=eSof87fG21Dd4COszfnbeXIxne3TWvw0mS
|
|
106
108
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
107
109
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
108
110
|
sglang/srt/distributed/naive_distributed.py,sha256=5Kcfapzz61G3TtScTZrHoWa4bf6Vr27GlMcBAGMz7tQ,3260
|
109
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
111
|
+
sglang/srt/distributed/parallel_state.py,sha256=RnondGDsfsbZxi2o8H1UivaoOMqDHiKVtDVb9HuOW44,65704
|
110
112
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
111
113
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
112
114
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=Q1kkKPKFPV0QMmKLyjOBlOnX8-Pr4UeGBZYkG6j0gc0,16570
|
@@ -122,16 +124,16 @@ sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=IrSrnpZnii0E
|
|
122
124
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
123
125
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
124
126
|
sglang/srt/entrypoints/context.py,sha256=aD-94xkD0komuGO5gtYUoJKCHdc4hAipMxQt04yVRGA,8030
|
125
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
127
|
+
sglang/srt/entrypoints/engine.py,sha256=7CBZly2Z1ekrBNbGHS187Yb0pj-Uuqw813s7oLrci8E,33496
|
126
128
|
sglang/srt/entrypoints/harmony_utils.py,sha256=01T-A5GBUm2b306PcxNEg2rfx4cykBcqNYrzcXTWBlc,13590
|
127
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
129
|
+
sglang/srt/entrypoints/http_server.py,sha256=_GEk6RgxlMWYUNXOx9he2OIFOs1-Qan1NrSm0EAGJ3M,49649
|
128
130
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
129
131
|
sglang/srt/entrypoints/tool.py,sha256=aAXEjBqkr5j6_IgRL8fZCKgoDPY2TikM20-LQXU9TaI,2709
|
130
132
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
131
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
133
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=jnHSYMJfCSTDCcIQpF1rWhJmU_It01CeiwiPlDd5-Vo,28673
|
132
134
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=epD6J7K72p6TP8o2dGYf-a76nXeF80vFhPRpWts6684,5445
|
133
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
134
|
-
sglang/srt/entrypoints/openai/serving_completions.py,sha256=
|
135
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=t5rZ0LxB1VXeclKex3cbzik4zmJ4ke1XyDmZOtRdJIk,43120
|
136
|
+
sglang/srt/entrypoints/openai/serving_completions.py,sha256=7aamrEWd7hu57c9mJ86Oe8AeI9qHF8TM74T6Gy-Efzw,17844
|
135
137
|
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=hqPt2ELpT1yQ8sBXo801aLJ3sExoPXs_K5ZQtC2vpAs,6274
|
136
138
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
137
139
|
sglang/srt/entrypoints/openai/serving_responses.py,sha256=aTdC98ZvqAjmGn6VntVw_c8OwtVYZnsewDjQGtKZ8q0,53398
|
@@ -140,8 +142,8 @@ sglang/srt/entrypoints/openai/tool_server.py,sha256=rRNGELPV5RHONp55MYkO4_b0NPsP
|
|
140
142
|
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
141
143
|
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
142
144
|
sglang/srt/eplb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
143
|
-
sglang/srt/eplb/eplb_manager.py,sha256=
|
144
|
-
sglang/srt/eplb/expert_distribution.py,sha256=
|
145
|
+
sglang/srt/eplb/eplb_manager.py,sha256=MRYyI3A2NgFvpv2R9lHXy_XS_KwZiZWPDxjpckh-H3A,4334
|
146
|
+
sglang/srt/eplb/expert_distribution.py,sha256=r7tqDZM-Ez2r6Wq7EnikoyB7fEAuPU60XI16r8DGa10,32705
|
145
147
|
sglang/srt/eplb/expert_location.py,sha256=SIinJLiDhS4mctTiMdIQzQZFchwrrvES0ufEVJ4OGeg,17076
|
146
148
|
sglang/srt/eplb/expert_location_dispatch.py,sha256=vA0o-7bXf847BQAVCqElWKEpofZLAIsir_d0pew2KNQ,4178
|
147
149
|
sglang/srt/eplb/expert_location_updater.py,sha256=eMtJVMCRklfvKPbFiDKy85f5J9s_krJbpRCSArYZjVs,21157
|
@@ -152,11 +154,12 @@ sglang/srt/eplb/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6Oi
|
|
152
154
|
sglang/srt/eplb/eplb_simulator/reader.py,sha256=OlsWqsuXqVQY7PfvvrP-vsl2Ww2Kg4vD_K9BltM_QHo,1828
|
153
155
|
sglang/srt/function_call/base_format_detector.py,sha256=FKBzsGFHfNl3Wvccsdvv9ftjbCZIyyjOLj2kHgKvX9g,15901
|
154
156
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
157
|
+
sglang/srt/function_call/deepseekv31_detector.py,sha256=hpRjjv219mH0v1PQpMvj_gezrP7PwvLiNbBKOTCSC3U,9731
|
155
158
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=DhO3tUX1nvFlfRkHJ1Vm_7OMXFFTvWBA9u9SZKFAwuQ,9710
|
156
159
|
sglang/srt/function_call/ebnf_composer.py,sha256=f5Lqn3mtTtJ7LCJXAurVw2k4Zp5LgbWywQv7GsxSoPw,15000
|
157
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
160
|
+
sglang/srt/function_call/function_call_parser.py,sha256=55bbToi2wWGmahfyDX1YeFpndNCwTa23ZdNsawMidbc,8333
|
158
161
|
sglang/srt/function_call/glm4_moe_detector.py,sha256=FS4Jhyt8_2xTTytNsQhzlNds2VQO_JIp3tKyCf7PtF0,6939
|
159
|
-
sglang/srt/function_call/gpt_oss_detector.py,sha256=
|
162
|
+
sglang/srt/function_call/gpt_oss_detector.py,sha256=uVhqYA5vATUIMaLPQX81qy2Fulwo6IlwCA_PbUg3gZY,8299
|
160
163
|
sglang/srt/function_call/kimik2_detector.py,sha256=u6GXTAcvqWstkuDgxZMeKlpp9zu3V4OTZ8yaplLxEGM,10109
|
161
164
|
sglang/srt/function_call/llama32_detector.py,sha256=trZja7IXc2IWUko5PRj7p4pRU6XCVjtxr-7qJNr0EWo,3647
|
162
165
|
sglang/srt/function_call/mistral_detector.py,sha256=Ts2HrJdu5r2lCCMVKPZfnCds9pt1K5H1EaOQrF_HD60,4686
|
@@ -165,42 +168,42 @@ sglang/srt/function_call/qwen25_detector.py,sha256=nv83_sipZMU6Vie3J4HeNiZVCSRU5
|
|
165
168
|
sglang/srt/function_call/qwen3_coder_detector.py,sha256=wRsGBH3TUdI3cubWEAmHDFYGojfHyt2bPpV2RCbKsyg,14297
|
166
169
|
sglang/srt/function_call/step3_detector.py,sha256=SAibrispu0peDQzqOG2-V93KGHtV6Ud7a38vlnhTunA,17442
|
167
170
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
168
|
-
sglang/srt/layers/activation.py,sha256=
|
171
|
+
sglang/srt/layers/activation.py,sha256=mAa6E8xTDs6RyuBO0kNXaIuWxOlKfu8jQH5YG9PblhY,8213
|
169
172
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
170
|
-
sglang/srt/layers/communicator.py,sha256=
|
173
|
+
sglang/srt/layers/communicator.py,sha256=RAP_oBwHBZdc5Knnb9FRozStODWc4toqDjU4wvekzHc,22625
|
171
174
|
sglang/srt/layers/dp_attention.py,sha256=35GQIpO8HpF9mtLQSJe2RW2a5rblTLvzAbr1CL0PbSg,15286
|
172
175
|
sglang/srt/layers/elementwise.py,sha256=PjYv7Sk-zKbG9WiGlYDKsxvNrnxT2N1Q8bA2BWvA1Uo,18771
|
173
176
|
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=hnVVS_VsWukTYhREubWs2KcJ1GjVMEI9ECqxqOMXZv8,6729
|
174
|
-
sglang/srt/layers/layernorm.py,sha256=
|
175
|
-
sglang/srt/layers/linear.py,sha256=
|
176
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
177
|
+
sglang/srt/layers/layernorm.py,sha256=hvfU36Q_SpHR7renSbXuI5WnENE_i5Z7TuU4dxRN7fw,10614
|
178
|
+
sglang/srt/layers/linear.py,sha256=evhlZ_aPFce-m89zYDeEfSrYAOoaMk5BC18vDjGPzjM,53508
|
179
|
+
sglang/srt/layers/logits_processor.py,sha256=jCLgKuU8r-T0ZdSjWEWNhtmx408f_NTKVCW20_dn2ZQ,26969
|
177
180
|
sglang/srt/layers/multimodal.py,sha256=vNswe0J0maeBiN8ehlmxfs-YYlrmMllYl6Nc_Y57Neg,5114
|
178
181
|
sglang/srt/layers/parameter.py,sha256=jCg0G-12GZqTa9gGOqEtVCsnnuBGnYg0VmF6pc6oCFg,17455
|
179
182
|
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
180
183
|
sglang/srt/layers/radix_attention.py,sha256=MpugwaqiY2zPTeg7FVW41OljljCXmYVvHZ2MvneF6PI,3745
|
181
|
-
sglang/srt/layers/rotary_embedding.py,sha256=
|
182
|
-
sglang/srt/layers/sampler.py,sha256=
|
184
|
+
sglang/srt/layers/rotary_embedding.py,sha256=lhGVkJpMtuWT_dLbYzgq6J7hXGIdvWiMWxWcww6oWv4,73927
|
185
|
+
sglang/srt/layers/sampler.py,sha256=RIcvSriJaHpFhjNPX3CzJzn4Lwy9H3MTPBeZjqAZq9o,11762
|
183
186
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
184
|
-
sglang/srt/layers/utils.py,sha256=
|
187
|
+
sglang/srt/layers/utils.py,sha256=E7PHisGiD9ZmLS4RWqCUZWxAQJbfc0WaTfRZ37gUlPI,1077
|
185
188
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=x0421kNUgnAb5LnkJR6O67vGZ0ikSD-ThluV3QGsZ_8,22673
|
186
189
|
sglang/srt/layers/attention/aiter_backend.py,sha256=XfZKrPFL1feerRMRL4jFoBGtbtoOD9gzKFCx8BomfJ4,43146
|
187
|
-
sglang/srt/layers/attention/ascend_backend.py,sha256=
|
190
|
+
sglang/srt/layers/attention/ascend_backend.py,sha256=zmEz1NfytWADYFmCGBVIGXhVAT5GX_z5fnC8-1r5pK4,23334
|
188
191
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=_vM05ddWy6SaoqWYPR8w5lflSE4MhcVFR271Q9EKK8E,3600
|
189
192
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=PB5BjbJHhmTg_t0kXfarTI6C3pPvKhBAqvCSGGajou0,9846
|
190
193
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
191
194
|
sglang/srt/layers/attention/dual_chunk_flashattention_backend.py,sha256=hCATQEhBATZpPhBMF-cCM9r6nxXA0dr3jOT_hTFS_T0,68656
|
192
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
193
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
194
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
195
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=3Jgapx8tVh2PbPVi6e5TX6eBttdOSm2V53TDbZRixr8,103779
|
196
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=KLN2t7qn0UtRMeNO9OPLgwyhj23KPAwx_z_OmJSN4uQ,54197
|
197
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=GNHvib_PaUO-JFmUcwRADzF7-4v61KFbvk0yEExMdhk,39556
|
195
198
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
196
|
-
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=
|
199
|
+
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=e5P0RxuS5tCfQe4S54WI5vuKjgDvTi4FcvPxgLsIk9k,4451
|
197
200
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
198
201
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
199
202
|
sglang/srt/layers/attention/tbo_backend.py,sha256=CBnSDUmDvT-Tbhi9NHNo1LLkgUAcIsWMJgKa-sAIKW8,9318
|
200
203
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzbyKOWHAVPOD9b0n0dEehwlos,9496
|
201
204
|
sglang/srt/layers/attention/triton_backend.py,sha256=fvcJLaJaM8JE9Q9Nkmn0dzdYnnYlwELCoxQGMoqS9Gk,41858
|
202
205
|
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=8MxCAzqsNuvO3mhFqTMXCJ0Tt0_82kFbBHie6m0ieDA,27588
|
203
|
-
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=
|
206
|
+
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=NBfuORA0oUlS_uB0I_ikHvUSVKsPbVVNdbvakyCQ3XY,19830
|
204
207
|
sglang/srt/layers/attention/utils.py,sha256=lx_jNw2VwlBe2VnDb1eXRRdN9WArw9rdWHTHqndUEFk,3174
|
205
208
|
sglang/srt/layers/attention/vision.py,sha256=PZUJuswPWvJ34NTtxJkcXnusojDv0pO0UhrsjL4SWYU,20268
|
206
209
|
sglang/srt/layers/attention/vision_utils.py,sha256=6hPPAt8p3SOm7tgHNUesnMLxvQiKbaOM5EK6K-ig5dI,2771
|
@@ -215,17 +218,17 @@ sglang/srt/layers/attention/wave_ops/decode_attention.py,sha256=C-W1hvswZ7ggDKp4
|
|
215
218
|
sglang/srt/layers/attention/wave_ops/extend_attention.py,sha256=aPNVsrhJD3OW7YF3jRm59IIawgA-bv_6GT91UPf5x5Y,3957
|
216
219
|
sglang/srt/layers/attention/wave_ops/prefill_attention.py,sha256=viTUit0rxjVV5UahuwmVAhmL66YRFJD4g1YhH_oRBu8,2344
|
217
220
|
sglang/srt/layers/moe/__init__.py,sha256=63TxUpSiUpVg1SDY1zdlTg3WFJzAc7WSndOViOmUv4E,835
|
218
|
-
sglang/srt/layers/moe/cutlass_moe.py,sha256=
|
221
|
+
sglang/srt/layers/moe/cutlass_moe.py,sha256=JKJED-4709ndP5AwhQ7Vi04GJjw5d9Xl_mWOsZPZ3U4,14298
|
219
222
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
220
223
|
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=rWyHMg0kYZhIdLWTJeC7pqRG9ywfeKqi47-OekNeF4Y,7306
|
221
224
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=8SAToE4B-22H5JsENZgJ1Io6QfE5-D9ItWLtbGksFQQ,3372
|
222
225
|
sglang/srt/layers/moe/rocm_moe_utils.py,sha256=07Z99bTV3B-b2Cbm-odhGpx2twxtnVpYvaDMBE1K3LM,4555
|
223
226
|
sglang/srt/layers/moe/router.py,sha256=eUNu_Uz5VB2FOZzZyYuZo5pokCVBS17_fcjHQbmvDSE,12181
|
224
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
227
|
+
sglang/srt/layers/moe/topk.py,sha256=r8pE6eJ8dprfZxaw8VcfrRvSp6_xDNPkr0tajmG_CZc,31349
|
225
228
|
sglang/srt/layers/moe/utils.py,sha256=omh9E6sF-KtrELEsE9y01Ash7FfQlstyE-97UtpH8qk,5998
|
226
229
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
227
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
228
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
230
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=Acg6dW-zVDQ95vuBVuzxb5SUFFxhLCewk_tVSZeuma8,46158
|
231
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=izQx9iy51r8nTla8_yfEnfQUzaW07RdIskXh2rJWAf8,27969
|
229
232
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=4NXZHbCw-G-uSnNUj4up0yh3xBDPnT-x0pdoIr0lku8,831
|
230
233
|
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=JKp89Cdl8a85tKzmJa4ah5VtxZzRNBSbY4cnsAtnvio,60803
|
231
234
|
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=jub7moptP9UjyRYJ2gPvY8HEnE41d_oFbZgjVvNsJxQ,39409
|
@@ -415,10 +418,12 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
415
418
|
"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
|
416
419
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=6JYGN4imwzIrQAEgboSO93wWYBuguzTgBjfTedq2c_Q,3250
|
417
420
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=dPe_9-JH0wF8q7Mhec4WWSLSGRE2gj_AQT3dnR3FREI,3257
|
421
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=ClPogINm5AsnjDqx6Hz_rHrmnnCdUPid-jYIdIgjZxs,3250
|
418
422
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json",sha256=RMYwqtB7hYeaCyuZ1feVnRhBGlN4jMcmNQX2hqUqBlk,3254
|
419
423
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=W8C1GtP4K43SK9128U52DD5WWofvPleAJE4us2Qju1k,3251
|
420
424
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=161,N=384,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json",sha256=RMYwqtB7hYeaCyuZ1feVnRhBGlN4jMcmNQX2hqUqBlk,3254
|
421
425
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=T6kCtCUytCxiW8JOLfEF3YgdCD9_mKccJ85IqT0b8LU,3253
|
426
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=64,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=QEk8bE-GieZltTiv3ig__ScM9Q_4K-c75UzIuDrGmPA,3232
|
422
427
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FEnjuvvky-cvW1iq8TPrfGOOH8y4rOEx4jlYZ4tqbDs,3253
|
423
428
|
sglang/srt/layers/moe/moe_runner/__init__.py,sha256=piJQmSz7BOBaxVd0gGMgRLzaD21r7PH1NEDOK5hktYk,97
|
424
429
|
sglang/srt/layers/moe/moe_runner/base.py,sha256=L7ZNcq6fQxMXQZypcxWKIe1j9ajoOKCsFRrF-UlHVaA,364
|
@@ -431,9 +436,9 @@ sglang/srt/layers/quantization/awq.py,sha256=-W4c4c5Df0h7d7mQKQFSJ9ZAxCtyWiOxpu5
|
|
431
436
|
sglang/srt/layers/quantization/awq_triton.py,sha256=4XwJbRNlFmlvjbMGtWF1Wvk26Kf96162vNEmuI5Kars,11737
|
432
437
|
sglang/srt/layers/quantization/base_config.py,sha256=taPmvTT2ZMzXShSHoAAYEAjF6_bvIcUY9Oa_ED_SpkY,7066
|
433
438
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=juOCfNFreRrSNwT3IWwj1f7AzlGDsR7WVl_DOCUznvU,13584
|
434
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
435
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
436
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
439
|
+
sglang/srt/layers/quantization/fp8.py,sha256=sWvsA1Ch_4JCTgZeM-ncf0jJUTQ4LF9_ruJNZOuKc9s,49634
|
440
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=Mgigb6GmF66oCrgjS97IvDDSacNYb0u-VYAf4FChhqM,54849
|
441
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=emYXdBdIi5peGtapIREr59IteiQcNTAgWULkU7Npzzo,27969
|
437
442
|
sglang/srt/layers/quantization/fpgemm_fp8.py,sha256=dq7rJz-QB9LovmZZLBMK8YJEOr05wjVrtWLmSTkXjYw,7004
|
438
443
|
sglang/srt/layers/quantization/gptq.py,sha256=fBcC-9v9GhLvU_oquKvmjD6O_p725SZPPOUtmDPz66E,39118
|
439
444
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
@@ -441,18 +446,18 @@ sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V
|
|
441
446
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
442
447
|
sglang/srt/layers/quantization/marlin_utils.py,sha256=aM3GU7b7rHNZE-tZjRSrtOaPWzSaMcLxck4he8MlEVI,26344
|
443
448
|
sglang/srt/layers/quantization/marlin_utils_fp8.py,sha256=iSjq-ikPOTU5plrWNTW4MletKLySIrNl5NhQmY6FyAo,12508
|
444
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
449
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=jWo_RzjZ993x7ZkV4c2MLBVMCqaL7lqaAlJpm9EDajU,52979
|
445
450
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=brU0nG6StgjGuuhOjpeoh-wJVZ1SUgbuHhiDR1hibbw,18905
|
446
|
-
sglang/srt/layers/quantization/mxfp4.py,sha256
|
447
|
-
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=
|
451
|
+
sglang/srt/layers/quantization/mxfp4.py,sha256=-HL6fBteyLSIc_y48kiroY1-OXpe7oJ8918hLiiON6s,31374
|
452
|
+
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=bGeCXlIOhmFZFGWp_lITkIRDEgGUaLpawDvMy1cTOmA,5389
|
448
453
|
sglang/srt/layers/quantization/petit.py,sha256=74Jn0eICq23v_b4rEctDaYTINtbqkdM6IXycT-_FbbI,8954
|
449
454
|
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
450
455
|
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
451
456
|
sglang/srt/layers/quantization/unquant.py,sha256=CxsOEYqYIfanKHo0ooFArbVz2ueX3vBWnYHE8gtnzdQ,12996
|
452
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
457
|
+
sglang/srt/layers/quantization/utils.py,sha256=d4eaS4-Z4q3GRgb4HDMr2EoWEdQCefrVdJufK6n_NQY,18509
|
453
458
|
sglang/srt/layers/quantization/w4afp8.py,sha256=345w-gCDes3dGqCUAmjyzXZemsIEWc_swJ7FyJyzFTI,11392
|
454
459
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=wzJi5jeTnbf-01iehOVTTCu_262rlMh9AQ2rogKWBmo,9981
|
455
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
460
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=cOKbhWxFlv6hw5dSs8ExPBXFcTwudwR26m3CAoOhCSs,35342
|
456
461
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
457
462
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=DsPCI82A4rqI6mjKo-WorIKUweppFV7-16Qku-zW9_g,25897
|
458
463
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=jWgfDtg5r6IRKJUpYXf5Tp13pWekoUCnYi8LMZ33PcU,25940
|
@@ -614,9 +619,9 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
614
619
|
"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
|
615
620
|
"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
|
616
621
|
sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py,sha256=esJMd0Yuj68t6QYOpmIFuiWP2J2dxTMC4bRBNH0Xk6I,26
|
617
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=
|
618
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=
|
619
|
-
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=
|
622
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=8BxWqX1WT7SvRRccBmx8CBVGiL_FIa923OlDYwzDcDM,7907
|
623
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=8C4xyO58N3Zl8h-fYddUpXDs3mnSqjYbaLt12cPB2XA,778
|
624
|
+
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=vCj5vdAshEB9mAgSUYXhgJ0bd1Ithmu_n4-m_IWUbd4,2531
|
620
625
|
sglang/srt/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
621
626
|
sglang/srt/layers/quantization/quark/quark.py,sha256=EqQvWzAc6nd_yl6UIMIwmozKif4I8fRNfBum040UUEQ,14613
|
622
627
|
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=yLRmytEwBMZd7ShzHVX6-w_8koyiRrvIxKx8g02qRZw,6789
|
@@ -638,49 +643,50 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVh
|
|
638
643
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=z9BB84Xu_MjwCu5v9Yvji-FkIzfEjDySAFybc4WYv7A,6483
|
639
644
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
640
645
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
641
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
646
|
+
sglang/srt/managers/cache_controller.py,sha256=WEaM01U0al13oSU7AHvwEBcmOy-1SmtPWbikgrPAx6g,33130
|
642
647
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
643
648
|
sglang/srt/managers/data_parallel_controller.py,sha256=VvEkidmYCGAFTv6upEHf_tyTvkM8xLhCyOnLJGWL6BQ,14592
|
644
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
645
|
-
sglang/srt/managers/io_struct.py,sha256=
|
646
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
649
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=YTl8ytxNf3an5sOAUjKTGcEKBJMKF7kQiViAw6eOoMw,13213
|
650
|
+
sglang/srt/managers/io_struct.py,sha256=ebAKRqBYj4slW25-dWs51JAW6caPcvuIMlSoJJZd8wo,40503
|
651
|
+
sglang/srt/managers/mm_utils.py,sha256=J5hahCJ7HAKhJtGzV6PRa5HB9B2NjYwWGYMqIgiGC60,29444
|
652
|
+
sglang/srt/managers/multi_tokenizer_mixin.py,sha256=smdzSwH-EW4zDNTJtkl6nXq6O_xH5EfW3iU3iSScUoM,22851
|
647
653
|
sglang/srt/managers/multimodal_processor.py,sha256=cnWpu2G79v1a6FJB_FriLxESgGUbfC3GptLmeRVVgew,1801
|
648
654
|
sglang/srt/managers/schedule_batch.py,sha256=9lhBnf-siQjsThD8FRyhiF50N-LOE7dfoPr1uzklnjQ,77170
|
649
655
|
sglang/srt/managers/schedule_policy.py,sha256=vh9BQW9tBv80LW4JApLE6smU2m4gy6cAEI25HVXiS60,22383
|
650
|
-
sglang/srt/managers/scheduler.py,sha256=
|
656
|
+
sglang/srt/managers/scheduler.py,sha256=7euNU5d089V4uCN7gDXHEz0eUzewQ5V7LrwAlvP5tKc,111061
|
651
657
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=zP8xU_UmU2H0AB6sEqvivDcDB1QDgTauNDYDIJ7Nez4,3683
|
652
658
|
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=31BbukSyUUPMNHLqRlS5sEiAv7Gi5VHFQ1TgxvcAdcw,10054
|
653
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=
|
659
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=CLwF58GTV7PkyYUoC-R7ROA-cZt8di9_9n2pajacxUY,31511
|
654
660
|
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=A67lC_U7HUCf_znatXK51orC8xeFNGouJ866HH_Y-yc,11402
|
655
661
|
sglang/srt/managers/scheduler_recv_skipper.py,sha256=8rVQCBjn9f26Th4XbeUS3fEsvo1GI029Me28wMjcKRY,1103
|
656
|
-
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=
|
662
|
+
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=uk7Dusr8EJBDRdcuQNIoedj0oP4tmSWrUbEqmjclwnk,5813
|
657
663
|
sglang/srt/managers/session_controller.py,sha256=FGADRGSkRmS76o_BQ2fivpgw0Q5Q-K0Ws3aezH41YSc,6041
|
658
664
|
sglang/srt/managers/template_manager.py,sha256=m_cy_KY5bOkDlh6IB9ocisy8N5r7abp4nfFnhruNxFg,11947
|
659
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
665
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=YaWYZ_FWjVPY1PaUqRBUgsREWgJ4YcN0n2CKaCXXhRw,88266
|
660
666
|
sglang/srt/managers/tp_worker.py,sha256=n_DqSD4JqOJYjdZrchOpmpuTazRw-AUrs6RPQYuAPyQ,11933
|
661
667
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=NXjrBT7lvdUlDDNFzEQyFYCerpqj92sNl2YynGhQj-Y,11118
|
662
668
|
sglang/srt/managers/utils.py,sha256=WbUdADEdiSOoQNfwjfU64mNaXoskEveBO1HP_t0FJtQ,5687
|
663
669
|
sglang/srt/mem_cache/allocator.py,sha256=5cLql3bTIFElYn9S6baBmKCO5L88W_sPC-TsTMZrk_g,18216
|
664
670
|
sglang/srt/mem_cache/allocator_ascend.py,sha256=i0KPCcFlzGkCIjW8ph3IPkBXAWTqq4-AeaoG1wR--lw,4471
|
665
671
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=hLS2ncTMAz7Kpdk5pNwn5c6g8b61_K9OCBL4Vj1xsYc,2801
|
666
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=
|
672
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=jbJeEEZ5_WYEF_AnDZIAu2sMD4hAGAd_24F980fjVwU,3199
|
667
673
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
668
|
-
sglang/srt/mem_cache/hicache_storage.py,sha256=
|
669
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
670
|
-
sglang/srt/mem_cache/lora_radix_cache.py,sha256=
|
671
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
672
|
-
sglang/srt/mem_cache/memory_pool_host.py,sha256=
|
674
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=eidtVRRsT8efqaEECXRLcxwJ7OomstzOctbqTucOLNg,7307
|
675
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=aL05axnc7qDy6FWMLbj76GaYIYjqooMEFYbSKiypJMA,28527
|
676
|
+
sglang/srt/mem_cache/lora_radix_cache.py,sha256=4NbK0Rc15kTiCOSsthyM6WsZarMK2MNhtsNqYMakJ5k,14369
|
677
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=EGZtQsgXDOuySeEBdV6jBIt9ZDvqMsErNPe6P5ifHh8,39540
|
678
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=d8TJqmOILaeub4maP09y20MwYf7KKobzv7pVrZ18CiA,26119
|
673
679
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=zPnQLQhBZ6zsUpCQPSoNkrB9EEvpoDQS4mU7c3sRWjE,2171
|
674
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=
|
675
|
-
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=
|
676
|
-
sglang/srt/mem_cache/swa_radix_cache.py,sha256=
|
680
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=U0KEjQNcwhdFWnXYTMhDkxpiazAD1ttbADEkGPHiiTU,19116
|
681
|
+
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=YuYt4xNzfmNNSkwaAk3VLWcZI74_XQobIyEgt96f7Qs,9284
|
682
|
+
sglang/srt/mem_cache/swa_radix_cache.py,sha256=hV5OOmAqu4UT80BVsu7lhGewcbq-u__JKx5T1lgxJyQ,40315
|
677
683
|
sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py,sha256=tQZpz-H6HxNAQe9mYqt6aX8mfDZyu_fbJTcCNK-Ns1M,7179
|
678
684
|
sglang/srt/mem_cache/storage/hf3fs/client_hf3fs.py,sha256=WV5M9UPPLUMMjU3Mpp6HBqyCQpGBuMyj-N5PwQcNo5k,5178
|
679
685
|
sglang/srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp,sha256=dDYPtxmL6OFhEyv_GuTgzkTDpBjcD0EK8kphnn7eaGc,1133
|
680
686
|
sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py,sha256=OfQMFwbbQg0pbC7rJktg5wz3YFhNsNOjsXCsAjrh6iU,16738
|
681
|
-
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=
|
687
|
+
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=RlVAloClfk_Cw4TjfokHl75YdgmtJ1FT7KdGA2QLXDk,13990
|
682
688
|
sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py,sha256=g2h0Woa2CK39pRTigHCVR_hq095dTaC70lCIAIs9THM,1089
|
683
|
-
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=
|
689
|
+
sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py,sha256=S0UAG86sVMDc4-LvzSZrLKeW0fec5D7py_sqe3JtXEk,10000
|
684
690
|
sglang/srt/mem_cache/storage/mooncake_store/unit_test.py,sha256=jMdJgU41VscKS-mn_AVZE8LQbb_3MWQ57i9V3OCWLI4,1007
|
685
691
|
sglang/srt/mem_cache/storage/nixl/hicache_nixl.py,sha256=bau9Jsp50lpEiy_osgb-dYzeoUkPWM03x7Q8z2BpKaU,9920
|
686
692
|
sglang/srt/mem_cache/storage/nixl/nixl_utils.py,sha256=KXkwMrbWwIOUOASINnUo4HyheiMd-93smmwGLv0CacU,7463
|
@@ -689,11 +695,11 @@ sglang/srt/metrics/collector.py,sha256=IfFr4RaamT3TPj9DjuEnvkdiBGKcIUCQSIIwd9GeZ
|
|
689
695
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
690
696
|
sglang/srt/model_executor/cuda_graph_runner.py,sha256=fZT_CQwhfu7kdnliKu5lYM2tunU0u3wBoIlCxm4FXCA,33920
|
691
697
|
sglang/srt/model_executor/forward_batch_info.py,sha256=2KBu9SChR-YwSNbw1mO3WR0P_EGQjFUC5rQfBx6js90,40707
|
692
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
698
|
+
sglang/srt/model_executor/model_runner.py,sha256=z24KnHB_GLD1XRtk9y_bLbN_T6ASWV8U-mV8u20Dkbw,78474
|
693
699
|
sglang/srt/model_executor/npu_graph_runner.py,sha256=isp2Plkf4b_gdjptYxJhTJk7JL21Jg-Md3hAYIuSVxM,3424
|
694
700
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
695
|
-
sglang/srt/model_loader/loader.py,sha256=
|
696
|
-
sglang/srt/model_loader/utils.py,sha256=
|
701
|
+
sglang/srt/model_loader/loader.py,sha256=RGcqzjQnOK2W-M3IURnmocNm8vZRG3ly_-76nye79Tg,60189
|
702
|
+
sglang/srt/model_loader/utils.py,sha256=KrOpyd_eefZC3zFnhnwxIKNTx9G-MmA6jIK3NQbTW0E,5002
|
697
703
|
sglang/srt/model_loader/weight_utils.py,sha256=dHEkm0c4w-lyhJBzktvmop-Psmkpb2KoTu7Azgw7VgU,38555
|
698
704
|
sglang/srt/models/arcee.py,sha256=Q6fujRESEnljzs8ls3XGsPtWxzfKfUa0QAvAekYzeBY,18981
|
699
705
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
@@ -706,7 +712,7 @@ sglang/srt/models/dbrx.py,sha256=117gwrB_o8VlACwDH5YlXkPfuS7t2Mh-nyJvpNpIYxs,159
|
|
706
712
|
sglang/srt/models/deepseek.py,sha256=M7nyHcAbTIs8vc1g6u00oy22-pp704Xp4T3clBzu4xM,17460
|
707
713
|
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
708
714
|
sglang/srt/models/deepseek_nextn.py,sha256=uoiJxAVl9DX7bQcjyuouAZz6W-cB1HMubcirTBghyR4,6115
|
709
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
715
|
+
sglang/srt/models/deepseek_v2.py,sha256=s5xrkzRtLujCKs-LUbvGl91c_QNZ4jO5Z0_6ER4tHdc,107544
|
710
716
|
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
711
717
|
sglang/srt/models/ernie4.py,sha256=7dP7_d0i86tv8Mp21Ew9RdsFr6TskIkm8UtUd8zFo00,16067
|
712
718
|
sglang/srt/models/ernie4_eagle.py,sha256=E7f-ygCcY8pIoyTMKFyVC2uRcG59-_RaQTO4gd5_uWI,7223
|
@@ -726,7 +732,7 @@ sglang/srt/models/glm4v.py,sha256=WtDvH4691H6IKrcGBrkBpweSm_iFK61bMEfvqpbblmc,23
|
|
726
732
|
sglang/srt/models/glm4v_moe.py,sha256=qgJtWyRI0dy9qcTMXHxhBZp-ghfghV3PLhpOXgSAW60,17313
|
727
733
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
728
734
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
729
|
-
sglang/srt/models/gpt_oss.py,sha256=
|
735
|
+
sglang/srt/models/gpt_oss.py,sha256=NoqSVjOlTzPR-TRpfViAAGyrk3lMIgyjL4RYVQQlhRY,44283
|
730
736
|
sglang/srt/models/granite.py,sha256=8q92shxVPAp_cJDohJATffSGd7Z0Oi-vF5jpY6DlK4s,19840
|
731
737
|
sglang/srt/models/granitemoe.py,sha256=j1rgZ62CbBioECjUblDCw_NneDQgY_QJODsI0fqXVO8,13779
|
732
738
|
sglang/srt/models/grok.py,sha256=8KCR13LtdnhswJrIwgb0sdFW0OxCA8GQ0fbN8gb856E,40518
|
@@ -742,11 +748,13 @@ sglang/srt/models/llama.py,sha256=tdyUon6icwzqo4XTAkFxVA2f82g80AGr9ZezK1uXmkM,28
|
|
742
748
|
sglang/srt/models/llama4.py,sha256=Fp5kqnk1v9Q1TOZH6uXkFKOOZLjV-B6FGoWpw7icO9I,19598
|
743
749
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
744
750
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
745
|
-
sglang/srt/models/llama_eagle3.py,sha256=
|
751
|
+
sglang/srt/models/llama_eagle3.py,sha256=Rwije5WiCollXFfv4KPIshorboNozLk1NZI3MqVPGjU,8786
|
746
752
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
747
753
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
748
754
|
sglang/srt/models/llava.py,sha256=xzYip_BAwpzSIdZre43LZiyTpFISa0ZCLdO6LUSbaCg,37702
|
749
755
|
sglang/srt/models/llavavid.py,sha256=-CSk0RJ2MQeb81sh-RISeVJFaI-XWY6nR6_I594MkME,12818
|
756
|
+
sglang/srt/models/longcat_flash.py,sha256=ZtVmyxmEG_ckDnWEj-rwa2q99sgB59XHMqiSpnmcKdw,40705
|
757
|
+
sglang/srt/models/longcat_flash_nextn.py,sha256=HxK_W0kcTrJu2WXMOJNYHajq8s-8qbHCWo7YBT-9e6E,29489
|
750
758
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
751
759
|
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
752
760
|
sglang/srt/models/minicpm.py,sha256=CzBJyZtfMpp8jvlEl29DHI7HLVq-CxuqP1UHwxIbaUI,14567
|
@@ -771,12 +779,12 @@ sglang/srt/models/phi4mm_utils.py,sha256=bW3un4x3SHDvSkAOHQEFO286FGdOPeKhBpJCOmN
|
|
771
779
|
sglang/srt/models/phimoe.py,sha256=EGaKFi02MZP20qFrILA4o2SJ0wb1HoJagFTSqVUbJcQ,19223
|
772
780
|
sglang/srt/models/pixtral.py,sha256=ZkZrV0mEfmbBdgRko2AvsMFZbAVskgp_5a5p1xCSRN0,16835
|
773
781
|
sglang/srt/models/qwen.py,sha256=j0OU3JjznWi_TbayI09yYGM-Obov6mQzJO82Hs0qBGw,11868
|
774
|
-
sglang/srt/models/qwen2.py,sha256=
|
775
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
782
|
+
sglang/srt/models/qwen2.py,sha256=kHNZCtT0jnQXC2aJN7Bp1DzaEzKWuhUAGL3hAmt8OU8,23598
|
783
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=NBoGulAvr2dKk6sfTJQ3NAOIFtBvncbLi_nsUOhnGuA,24084
|
776
784
|
sglang/srt/models/qwen2_audio.py,sha256=SOOsspU7J6eM-iSkms5op0nWhoxJd6QxmwXU2aQBEEQ,7776
|
777
785
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
778
786
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
779
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
787
|
+
sglang/srt/models/qwen2_moe.py,sha256=0Na7Zy6ukQl6IPCzQajunP2GYySm_NWuqCD-fQdWWX0,26756
|
780
788
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
781
789
|
sglang/srt/models/qwen2_vl.py,sha256=ZRAL32Ymt4ZCBqB0JorXAm4ZBrECZ9EbaXKaTSikkQM,21366
|
782
790
|
sglang/srt/models/qwen3.py,sha256=xw-OsNRsC3nO5IR2OG7nSfupIiKQOxC_0VFQ4lKcbfc,19123
|
@@ -788,13 +796,13 @@ sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9
|
|
788
796
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
789
797
|
sglang/srt/models/step3_vl.py,sha256=joJmGukbGThLvwwbwrI4mCEVONH_U1dzFLWdpeJFoKo,35654
|
790
798
|
sglang/srt/models/torch_native_llama.py,sha256=C1WpLn47q0l7IQa0k-Gvbs914FBcpKzqTIX-uvibq-w,18320
|
791
|
-
sglang/srt/models/transformers.py,sha256=
|
799
|
+
sglang/srt/models/transformers.py,sha256=laA2h39MPeiAWKv4DEg0ydre-1pyXWFSRga-nwy1HUk,10244
|
792
800
|
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
793
801
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
794
802
|
sglang/srt/models/xverse_moe.py,sha256=nBtG_PAK8wcp1tW2l2Zby2oEOmtWAYzH5COH-_N5IAM,17072
|
795
803
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
796
804
|
sglang/srt/multimodal/mm_utils.py,sha256=6bV1_a7Iet9W0y3qdd0E-hFM78zalIzNZCYbLzJX2y8,12640
|
797
|
-
sglang/srt/multimodal/processors/base_processor.py,sha256=
|
805
|
+
sglang/srt/multimodal/processors/base_processor.py,sha256=G25SF9bIyoQ13v7Qsb2ZDWTBq-BJ8Sa9okGZPPsS2TM,24518
|
798
806
|
sglang/srt/multimodal/processors/clip.py,sha256=5nXZuQYbyf-5mlqPwjhQrlWqxvswImWZQXivChsiHfQ,1057
|
799
807
|
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=Pymag9f0U5L_bBOTFs2q94BbuPJ-VwqSixs3meO0nsM,2569
|
800
808
|
sglang/srt/multimodal/processors/gemma3.py,sha256=7aD6cR60iSC_MqjzdCDMAgtrb_cmy9YJyqLgVRClBT8,1986
|
@@ -819,15 +827,15 @@ sglang/srt/sampling/sampling_params.py,sha256=HbVcCeSXgPW19MRB-v0FTG1D-zHDAY6-to
|
|
819
827
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
820
828
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
821
829
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
822
|
-
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=
|
830
|
+
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=Romk41ahToaVlNMnnd1Enko7_kRA4KdMGO94qnEbDHA,6061
|
823
831
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
824
832
|
sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18nst2oOD8HnA2mZ4,12859
|
825
833
|
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=jOIQDXsZ_CbxiTXnJjKtzYfOpc7-67dWwCaNcrv1Ebc,13938
|
826
834
|
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=QuPI0S85KirTlJArLpJXpywv7XQLborDGLFYwLUBnwk,15459
|
827
835
|
sglang/srt/speculative/eagle_utils.py,sha256=H-2aqm3REztUXLnmhi31ck3TWPPMVKc2CUkWBPsFK44,47785
|
828
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
836
|
+
sglang/srt/speculative/eagle_worker.py,sha256=7tjpKhFxColzlUZ-sONDYGMvto5uInzFxGBcj8IY6dM,42197
|
829
837
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
830
|
-
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=
|
838
|
+
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=KJwr6Xlc7AdHegMTnAVKJlPpW59Z7AE27GTzFL78GwI,6222
|
831
839
|
sglang/srt/weight_sync/tensor_bucket.py,sha256=vp_LRrhULNnxiw9Tf56FcEckgUg07lifgv1lasG6y7o,3695
|
832
840
|
sglang/srt/weight_sync/utils.py,sha256=43zl3u8Svzj49p7Sk78xp7SWW83mlr3EH-OZFGUGy5w,4157
|
833
841
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
@@ -862,9 +870,9 @@ sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
|
|
862
870
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
863
871
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
864
872
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
865
|
-
sglang/test/attention/test_trtllm_mla_backend.py,sha256=
|
866
|
-
sglang-0.5.
|
867
|
-
sglang-0.5.
|
868
|
-
sglang-0.5.
|
869
|
-
sglang-0.5.
|
870
|
-
sglang-0.5.
|
873
|
+
sglang/test/attention/test_trtllm_mla_backend.py,sha256=quZ6SYuEH7J1YMcF8YO1_bwSNMz1gecpWRGauYjbUeA,42055
|
874
|
+
sglang-0.5.2rc0.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
875
|
+
sglang-0.5.2rc0.dist-info/METADATA,sha256=6S-9JaZ2NMphKGxZVRyfEQWUwyjRY3I0a3HY4qNLU00,28157
|
876
|
+
sglang-0.5.2rc0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
877
|
+
sglang-0.5.2rc0.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
878
|
+
sglang-0.5.2rc0.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|