sglang 0.4.9.post3__py3-none-any.whl → 0.4.9.post5__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sglang/lang/chat_template.py +21 -0
- sglang/srt/_custom_ops.py +29 -1
- sglang/srt/configs/internvl.py +3 -0
- sglang/srt/configs/model_config.py +5 -1
- sglang/srt/constrained/base_grammar_backend.py +10 -2
- sglang/srt/constrained/xgrammar_backend.py +7 -5
- sglang/srt/conversation.py +17 -2
- sglang/srt/debug_utils/__init__.py +0 -0
- sglang/srt/debug_utils/dump_comparator.py +131 -0
- sglang/srt/debug_utils/dumper.py +108 -0
- sglang/srt/debug_utils/text_comparator.py +172 -0
- sglang/srt/disaggregation/common/conn.py +34 -6
- sglang/srt/disaggregation/decode_schedule_batch_mixin.py +13 -1
- sglang/srt/disaggregation/mini_lb.py +3 -2
- sglang/srt/disaggregation/mooncake/conn.py +65 -20
- sglang/srt/disaggregation/mooncake/transfer_engine.py +4 -2
- sglang/srt/disaggregation/nixl/conn.py +17 -13
- sglang/srt/disaggregation/prefill.py +13 -1
- sglang/srt/distributed/device_communicators/custom_all_reduce.py +3 -91
- sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py +96 -1
- sglang/srt/distributed/device_communicators/quick_all_reduce.py +273 -0
- sglang/srt/distributed/device_communicators/shm_broadcast.py +12 -5
- sglang/srt/distributed/parallel_state.py +70 -15
- sglang/srt/entrypoints/engine.py +5 -9
- sglang/srt/entrypoints/http_server.py +20 -32
- sglang/srt/entrypoints/openai/protocol.py +3 -3
- sglang/srt/entrypoints/openai/serving_chat.py +148 -72
- sglang/srt/function_call/base_format_detector.py +74 -12
- sglang/srt/function_call/deepseekv3_detector.py +26 -11
- sglang/srt/function_call/ebnf_composer.py +105 -66
- sglang/srt/function_call/function_call_parser.py +6 -4
- sglang/srt/function_call/glm4_moe_detector.py +164 -0
- sglang/srt/function_call/kimik2_detector.py +41 -16
- sglang/srt/function_call/llama32_detector.py +6 -3
- sglang/srt/function_call/mistral_detector.py +11 -3
- sglang/srt/function_call/pythonic_detector.py +16 -14
- sglang/srt/function_call/qwen25_detector.py +12 -3
- sglang/srt/function_call/{qwen3_detector.py → qwen3_coder_detector.py} +11 -9
- sglang/srt/layers/activation.py +11 -3
- sglang/srt/layers/attention/base_attn_backend.py +3 -1
- sglang/srt/layers/attention/hybrid_attn_backend.py +100 -0
- sglang/srt/layers/attention/vision.py +56 -8
- sglang/srt/layers/communicator.py +12 -12
- sglang/srt/layers/dp_attention.py +72 -24
- sglang/srt/layers/layernorm.py +26 -1
- sglang/srt/layers/logits_processor.py +46 -25
- sglang/srt/layers/moe/ep_moe/layer.py +172 -206
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=160,N=320,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=320,device_name=NVIDIA_H20-3e.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +25 -224
- sglang/srt/layers/moe/fused_moe_triton/layer.py +38 -48
- sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py +11 -8
- sglang/srt/layers/moe/topk.py +88 -34
- sglang/srt/layers/multimodal.py +11 -8
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +2 -9
- sglang/srt/layers/quantization/fp8.py +25 -247
- sglang/srt/layers/quantization/fp8_kernel.py +78 -48
- sglang/srt/layers/quantization/modelopt_quant.py +33 -14
- sglang/srt/layers/quantization/unquant.py +24 -76
- sglang/srt/layers/quantization/utils.py +0 -9
- sglang/srt/layers/quantization/w4afp8.py +68 -17
- sglang/srt/layers/radix_attention.py +5 -3
- sglang/srt/lora/lora_manager.py +133 -169
- sglang/srt/lora/lora_registry.py +188 -0
- sglang/srt/lora/mem_pool.py +2 -2
- sglang/srt/managers/cache_controller.py +62 -13
- sglang/srt/managers/io_struct.py +19 -1
- sglang/srt/managers/mm_utils.py +154 -35
- sglang/srt/managers/multimodal_processor.py +3 -14
- sglang/srt/managers/schedule_batch.py +27 -11
- sglang/srt/managers/scheduler.py +48 -26
- sglang/srt/managers/tokenizer_manager.py +62 -28
- sglang/srt/managers/tp_worker.py +5 -4
- sglang/srt/mem_cache/allocator.py +67 -7
- sglang/srt/mem_cache/hicache_storage.py +17 -1
- sglang/srt/mem_cache/hiradix_cache.py +35 -18
- sglang/srt/mem_cache/memory_pool_host.py +3 -0
- sglang/srt/model_executor/cuda_graph_runner.py +61 -25
- sglang/srt/model_executor/forward_batch_info.py +201 -29
- sglang/srt/model_executor/model_runner.py +109 -37
- sglang/srt/models/deepseek_v2.py +63 -30
- sglang/srt/models/glm4_moe.py +1035 -0
- sglang/srt/models/glm4_moe_nextn.py +167 -0
- sglang/srt/models/interns1.py +328 -0
- sglang/srt/models/internvl.py +143 -47
- sglang/srt/models/llava.py +9 -5
- sglang/srt/models/minicpmo.py +4 -1
- sglang/srt/models/mllama4.py +10 -3
- sglang/srt/models/qwen2_moe.py +2 -6
- sglang/srt/models/qwen3_moe.py +6 -8
- sglang/srt/multimodal/processors/base_processor.py +20 -6
- sglang/srt/multimodal/processors/clip.py +2 -2
- sglang/srt/multimodal/processors/deepseek_vl_v2.py +2 -2
- sglang/srt/multimodal/processors/gemma3.py +2 -2
- sglang/srt/multimodal/processors/gemma3n.py +2 -2
- sglang/srt/multimodal/processors/internvl.py +21 -8
- sglang/srt/multimodal/processors/janus_pro.py +2 -2
- sglang/srt/multimodal/processors/kimi_vl.py +2 -2
- sglang/srt/multimodal/processors/llava.py +4 -4
- sglang/srt/multimodal/processors/minicpm.py +2 -3
- sglang/srt/multimodal/processors/mlama.py +2 -2
- sglang/srt/multimodal/processors/mllama4.py +18 -111
- sglang/srt/multimodal/processors/phi4mm.py +2 -2
- sglang/srt/multimodal/processors/pixtral.py +2 -2
- sglang/srt/multimodal/processors/qwen_audio.py +2 -2
- sglang/srt/multimodal/processors/qwen_vl.py +2 -2
- sglang/srt/multimodal/processors/vila.py +3 -1
- sglang/srt/reasoning_parser.py +48 -5
- sglang/srt/sampling/sampling_batch_info.py +6 -5
- sglang/srt/server_args.py +132 -60
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +33 -28
- sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +37 -36
- sglang/srt/speculative/eagle_utils.py +51 -23
- sglang/srt/speculative/eagle_worker.py +59 -44
- sglang/srt/two_batch_overlap.py +9 -5
- sglang/srt/utils.py +113 -69
- sglang/srt/weight_sync/utils.py +119 -0
- sglang/test/runners.py +4 -0
- sglang/test/test_activation.py +50 -1
- sglang/test/test_utils.py +65 -5
- sglang/utils.py +19 -0
- sglang/version.py +1 -1
- {sglang-0.4.9.post3.dist-info → sglang-0.4.9.post5.dist-info}/METADATA +6 -6
- {sglang-0.4.9.post3.dist-info → sglang-0.4.9.post5.dist-info}/RECORD +127 -114
- sglang/srt/debug_utils.py +0 -74
- {sglang-0.4.9.post3.dist-info → sglang-0.4.9.post5.dist-info}/WHEEL +0 -0
- {sglang-0.4.9.post3.dist-info → sglang-0.4.9.post5.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.9.post3.dist-info → sglang-0.4.9.post5.dist-info}/top_level.txt +0 -0
@@ -9,11 +9,11 @@ sglang/compile_deep_gemm.py,sha256=H118s76CKdpZr-cDeFfBCePe7--c_teEBNVIzchYVSo,6
|
|
9
9
|
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
10
10
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
11
11
|
sglang/profiler.py,sha256=tEHzHerXC-ymk4OrkoUcMbgcGHmb8VESthsNSP2Yx9w,4417
|
12
|
-
sglang/utils.py,sha256=
|
13
|
-
sglang/version.py,sha256=
|
12
|
+
sglang/utils.py,sha256=DSMD5Ch-gmkIO6Dh4JAmBMtRAu4JZ7uYO0NUMprGVO4,16770
|
13
|
+
sglang/version.py,sha256=GBi71Z9Lv3isXS33OtWCtTjl5apAGantvWQRrye9bj0,28
|
14
14
|
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
15
15
|
sglang/eval/loogle_eval.py,sha256=-CC2s2kh5qUoDrHRkQVkC_jNvBgNojXbf456ny5s78s,4557
|
16
|
-
sglang/lang/chat_template.py,sha256=
|
16
|
+
sglang/lang/chat_template.py,sha256=ZNcuDvDZE9781tQqfKpptck_zJVK0aggq7IxrNHltao,21934
|
17
17
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
18
18
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
19
19
|
sglang/lang/interpreter.py,sha256=JneG-Yw-XyOTBZCIoxTiQluQjAlSz1YswnV0l6pqVPo,34811
|
@@ -26,24 +26,23 @@ sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThc
|
|
26
26
|
sglang/lang/backend/openai.py,sha256=YFs7pCDK6_DoYmjTa-vgDVdaeE4PYr7E-sIC1q7vAns,16422
|
27
27
|
sglang/lang/backend/runtime_endpoint.py,sha256=oxLCLXCa26VfKyPV-wbRjLrQvqTG8NzoaVgwczzyIYc,17481
|
28
28
|
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
29
|
-
sglang/srt/_custom_ops.py,sha256=
|
29
|
+
sglang/srt/_custom_ops.py,sha256=9GPNUyqnybgvUnzdQ8n5_NgluHmQNw0Gptos0iLPfrY,5342
|
30
30
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
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=ocpOVHIKV2C0Unp3ALwtW71HZo3tgaCzadXp62Omqdw,41604
|
34
34
|
sglang/srt/custom_op.py,sha256=7OPQAZe3PqDXk-xM0Wxl7pm9cazilNJfkNiYIWztWgI,3198
|
35
|
-
sglang/srt/debug_utils.py,sha256=slaFOY4BYDBFatkfu8FZlzai-u4LFS-5GUzdr-t50zE,2241
|
36
35
|
sglang/srt/hf_transformers_utils.py,sha256=UiGjp70ZpTaZDJ99Roc-2DTkxV3gR-2oJjjaNY9Ekh4,12391
|
37
36
|
sglang/srt/jinja_template_utils.py,sha256=0c6nQjkGukmyXsqQ9r85R5QK9CafnjqXyrXF4K3aFhE,7177
|
38
37
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
39
38
|
sglang/srt/operations.py,sha256=ddQ8KO63L73OciaR8MZ9h2h83gKVY4-WuWgeEGowPJA,5346
|
40
39
|
sglang/srt/operations_strategy.py,sha256=Pwd2sKeRtKh9WJXgzlNr2tU9y6YMcI3MDLbatHqlMws,7145
|
41
40
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
42
|
-
sglang/srt/reasoning_parser.py,sha256=
|
43
|
-
sglang/srt/server_args.py,sha256=
|
41
|
+
sglang/srt/reasoning_parser.py,sha256=6lkrkR8Q25EU3VAE0jjSq__361e3CkX0gJIieSfjsZk,9247
|
42
|
+
sglang/srt/server_args.py,sha256=hfPgshfRHHq-_wI4jjMAjMGeXqmr3ZSBB_3ZVW7c8Bo,85937
|
44
43
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
45
|
-
sglang/srt/two_batch_overlap.py,sha256=
|
46
|
-
sglang/srt/utils.py,sha256=
|
44
|
+
sglang/srt/two_batch_overlap.py,sha256=Lx4bIXJb3hd9vzuJbmp3Crf4I8_NrT9fUbs-4LRzQXk,28711
|
45
|
+
sglang/srt/utils.py,sha256=6YkLoFlKyLpCNlk6zzaM5ys5_dMRTMOWNoLH09oEsOs,93321
|
47
46
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
48
47
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
49
48
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -51,12 +50,12 @@ sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11
|
|
51
50
|
sglang/srt/configs/deepseekvl2.py,sha256=sYMmoy5_LlDXht7MTi4QGYOaiE8iMGUO44bnuOu4i8I,23683
|
52
51
|
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
53
52
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
54
|
-
sglang/srt/configs/internvl.py,sha256=
|
53
|
+
sglang/srt/configs/internvl.py,sha256=meLG4M2s27bPI-yTleRimPdAuOH1DjiVwUf2U6vXzno,27844
|
55
54
|
sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsrKI,19156
|
56
55
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
57
56
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
58
57
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
59
|
-
sglang/srt/configs/model_config.py,sha256=
|
58
|
+
sglang/srt/configs/model_config.py,sha256=X7xirRQx1M0OhM7L-cOPJqHfBFIOfiZiiov3E847nqY,28613
|
60
59
|
sglang/srt/configs/update_config.py,sha256=D-myV9Ombwp6wTF0RX9qUO6m5rxFiUcyse32FQADG28,4787
|
61
60
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
62
61
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
@@ -67,19 +66,23 @@ sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8
|
|
67
66
|
sglang/srt/connector/serde/__init__.py,sha256=MvBJ7FBJtnou-AD-EdsCdAIDCcA8kWvUNuRViILVJ-0,718
|
68
67
|
sglang/srt/connector/serde/safe_serde.py,sha256=Iv_mFsDvk-cXuw0WTykBZ2yGxW0jb82DwVqC7r3RmAU,750
|
69
68
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
70
|
-
sglang/srt/constrained/base_grammar_backend.py,sha256=
|
69
|
+
sglang/srt/constrained/base_grammar_backend.py,sha256=ATWX1LKp3GjUDVkauEaSc3MnS8Bt6hOiHUgeYDZtgNo,7059
|
71
70
|
sglang/srt/constrained/llguidance_backend.py,sha256=Au8G8x4EB39w7k9-GFLP2hOPETyeAPw53RRZYdLimpA,6191
|
72
71
|
sglang/srt/constrained/outlines_backend.py,sha256=4Er45scnqHuJQ14kggsVX3RoHlaUD9t0ALIoWDQEmFg,6913
|
73
72
|
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
74
73
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
75
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=
|
74
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=y_pmPUHEkqLM1BCHcakRYC99j2_hzrsivd5uJIKeuJE,8149
|
76
75
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
76
|
+
sglang/srt/debug_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
77
|
+
sglang/srt/debug_utils/dump_comparator.py,sha256=8ZPwP0zojfRHvPiSKgpESYFcC3tR-sBjIej5SotOmpg,3947
|
78
|
+
sglang/srt/debug_utils/dumper.py,sha256=eyrg5lmwyYF88kn8b06kpu1__aGnWb6CLM8fxywtooI,3158
|
79
|
+
sglang/srt/debug_utils/text_comparator.py,sha256=pg58q3fzsnd3rJKRgZTdcOviOtAv8pSYZdwf-TLffMM,5522
|
77
80
|
sglang/srt/disaggregation/decode.py,sha256=P-0OyFjjDfthEVhlJugdscWST_uoOVmHZlSlx9NYLmE,34242
|
78
|
-
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=
|
81
|
+
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=sUXmqiJGwuYoJvZjRCgTMVEN7bLefnEUlCTJpVA6ecI,6416
|
79
82
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
80
83
|
sglang/srt/disaggregation/launch_lb.py,sha256=mcbAztN4gnHevw_T5R2_nWsymsDEY9vHkm7OJ1vr6cc,4211
|
81
|
-
sglang/srt/disaggregation/mini_lb.py,sha256=
|
82
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
84
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=bpnz6d90nv7vAoiPxmxFKlM1Gjct0R4IPkF9SwwBk9I,14504
|
85
|
+
sglang/srt/disaggregation/prefill.py,sha256=u8eKfWPuXiHDqFCWmhqlYhco3wy7nt5DjSmekwJTkhQ,24286
|
83
86
|
sglang/srt/disaggregation/utils.py,sha256=ql5p9yjBCRcR0YMgcgRK6tH0kPGvLNTUgeXBr_BUcoI,12198
|
84
87
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
85
88
|
sglang/srt/disaggregation/ascend/conn.py,sha256=FOYrGtEhj58iTjhYT1eP96DpyxBLFFR87icqYCzWmCY,1215
|
@@ -87,37 +90,38 @@ sglang/srt/disaggregation/ascend/transfer_engine.py,sha256=_4PszsQL6wICdg5cqpR2N
|
|
87
90
|
sglang/srt/disaggregation/base/__init__.py,sha256=4VwUv0aWxwmVL1049XK82aLTNxmt0WY5RPy9li-wyVk,160
|
88
91
|
sglang/srt/disaggregation/base/conn.py,sha256=CPDAoAkYaFtVPLa1QROfwipSVe7MH6omzIBHzo8TSYk,2811
|
89
92
|
sglang/srt/disaggregation/common/__init__.py,sha256=7yl-EGLMVKRpBUaGF_7lwAsw2J_mqpRZV0238VGxD9o,126
|
90
|
-
sglang/srt/disaggregation/common/conn.py,sha256=
|
93
|
+
sglang/srt/disaggregation/common/conn.py,sha256=3YJVviObY3fkSfQbVxE5lgcqMmqM5nDjWfEjS5-SW6I,17054
|
91
94
|
sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeKVPMWPcB5ywbE,1194
|
92
95
|
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
93
96
|
sglang/srt/disaggregation/fake/conn.py,sha256=oD1DArn1yDFZCu-X6p93uSLlAXEkt9lYxERICMznxGw,2286
|
94
97
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
95
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
96
|
-
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256
|
98
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=4TnmzcCDDm15j3XFFw_n_awq958-ljVahy8nC3CuFdc,61842
|
99
|
+
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=-ulLhz6DBDsmEjwNjjH5Pj8ngZKISgwBc_zL3ViGDN0,4761
|
97
100
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
98
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
101
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=eSof87fG21Dd4COszfnbeXIxne3TWvw0mSvCOkjsBZc,20323
|
99
102
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
100
103
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
101
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
104
|
+
sglang/srt/distributed/parallel_state.py,sha256=crlAUplgruIVrDk6jFZ0-6M3W6FXX67buZ3T-4XDgFA,58530
|
102
105
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
103
106
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
104
|
-
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=
|
105
|
-
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=
|
107
|
+
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=p-GLYYnMSjcUvK30qcwYhXEJwGrOz6rR99p_23SWFj8,16570
|
108
|
+
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=Fx9D70NO2dplyuqOxTasMwkzONN3wfC4WOny3tWSbPA,14159
|
106
109
|
sglang/srt/distributed/device_communicators/hpu_communicator.py,sha256=gPjEH1-izoby5uDrfUlzNf21luPT0Ow7pJjhCRKnHy8,1728
|
107
110
|
sglang/srt/distributed/device_communicators/npu_communicator.py,sha256=bRXN1Md_4SHQGzQYZa2GrHv2zbIU5vSpkueHiAZL1xQ,1345
|
108
111
|
sglang/srt/distributed/device_communicators/pymscclpp.py,sha256=8Pgehd02v-BpHixTTB4OB9ZlxA7fyXiPF4Xp9F_heyU,10890
|
109
112
|
sglang/srt/distributed/device_communicators/pynccl.py,sha256=obXyCaZznZHSt486XCnEOBNG3Cen7ysuuMuGRlTTl-8,10095
|
110
113
|
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6EMz-oPS9J16WHo2Q_SRL1DtlJKK63Hfg,15349
|
111
|
-
sglang/srt/distributed/device_communicators/
|
114
|
+
sglang/srt/distributed/device_communicators/quick_all_reduce.py,sha256=4j1_E4azoxfd8wxtfFmt9rvbQncl8ny6wmTMl6gAkp0,9932
|
115
|
+
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=IrSrnpZnii0EJTS1CYRwEwE7gyHxJBVgI2QuJS3AKW0,20906
|
112
116
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
113
117
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
114
|
-
sglang/srt/entrypoints/engine.py,sha256
|
115
|
-
sglang/srt/entrypoints/http_server.py,sha256
|
118
|
+
sglang/srt/entrypoints/engine.py,sha256=dGazuzKYxQSfXjea1aeSqaZubvLER0EVZzD7CvpHq9A,31595
|
119
|
+
sglang/srt/entrypoints/http_server.py,sha256=-unKM0lCK7Scd3LLTxLl-3vhit6lMb-wWfjLywelRy0,37214
|
116
120
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
117
121
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
118
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
122
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=UUc5oJ7E60fYoUqMb53H85i7HHhDfmYLIFZidhNrP0s,19147
|
119
123
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=5NJ2S_6B2NFSwn4nLp6eaeJ5iC3IcQzMEY9lW_gPcdA,5246
|
120
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
124
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=MbLFLLFhvCTpJ_j7t03seXHHoFjlXCZtzVjSg_L7iz8,39841
|
121
125
|
sglang/srt/entrypoints/openai/serving_completions.py,sha256=emIutVmnJgOgGRuAqdB80-kVHUfQbE67n1VS-76o4QY,16690
|
122
126
|
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=hqPt2ELpT1yQ8sBXo801aLJ3sExoPXs_K5ZQtC2vpAs,6274
|
123
127
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
@@ -135,31 +139,32 @@ sglang/srt/eplb/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9e
|
|
135
139
|
sglang/srt/eplb/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
136
140
|
sglang/srt/eplb/eplb_simulator/__init__.py,sha256=HIZaXqsvsOCMMJ81dSs1afSGZ5G6OiOZEtHpltyzzjY,21
|
137
141
|
sglang/srt/eplb/eplb_simulator/reader.py,sha256=OlsWqsuXqVQY7PfvvrP-vsl2Ww2Kg4vD_K9BltM_QHo,1828
|
138
|
-
sglang/srt/function_call/base_format_detector.py,sha256=
|
142
|
+
sglang/srt/function_call/base_format_detector.py,sha256=FKBzsGFHfNl3Wvccsdvv9ftjbCZIyyjOLj2kHgKvX9g,15901
|
139
143
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
140
|
-
sglang/srt/function_call/deepseekv3_detector.py,sha256=
|
141
|
-
sglang/srt/function_call/ebnf_composer.py,sha256=
|
142
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
143
|
-
sglang/srt/function_call/
|
144
|
-
sglang/srt/function_call/
|
145
|
-
sglang/srt/function_call/
|
146
|
-
sglang/srt/function_call/
|
147
|
-
sglang/srt/function_call/
|
148
|
-
sglang/srt/function_call/
|
144
|
+
sglang/srt/function_call/deepseekv3_detector.py,sha256=WzJbwCe8DoOi8guX9pdVMd70CViVrwoaxi8PZwIC9pg,9712
|
145
|
+
sglang/srt/function_call/ebnf_composer.py,sha256=HvLTgfNnBNKFKW-L36DKh07yRLbdTYjSfbTcLRUxZUc,14948
|
146
|
+
sglang/srt/function_call/function_call_parser.py,sha256=YTFGRA0rJf18ox2veLzmSBEm85QiZsPMNvNwiq8-iyo,8009
|
147
|
+
sglang/srt/function_call/glm4_moe_detector.py,sha256=TD67qS7T-9iR4-P5fhrUbqqYWEYVTb30dDNd7lGj4Rk,6934
|
148
|
+
sglang/srt/function_call/kimik2_detector.py,sha256=7unW_GwH7I6jrh2BZbw22mWRZzQ0OMTYDz_xVX5abPU,10116
|
149
|
+
sglang/srt/function_call/llama32_detector.py,sha256=trZja7IXc2IWUko5PRj7p4pRU6XCVjtxr-7qJNr0EWo,3647
|
150
|
+
sglang/srt/function_call/mistral_detector.py,sha256=Ts2HrJdu5r2lCCMVKPZfnCds9pt1K5H1EaOQrF_HD60,4686
|
151
|
+
sglang/srt/function_call/pythonic_detector.py,sha256=yAatItKtVDf9uhlB78wPWKP3fbefLJDNGGzFV5ey-YA,8756
|
152
|
+
sglang/srt/function_call/qwen25_detector.py,sha256=nv83_sipZMU6Vie3J4HeNiZVCSRU5ei7601j50779HA,5181
|
153
|
+
sglang/srt/function_call/qwen3_coder_detector.py,sha256=3QAoK9W3YFPrx_j3xIsDpmQSnbX0BixMAlJ6BoNJo8o,5517
|
149
154
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
150
|
-
sglang/srt/layers/activation.py,sha256=
|
155
|
+
sglang/srt/layers/activation.py,sha256=uhfhh10N5iLoLEBCvFPRjCfDxu5jXe1ehHJb3ISIjig,7840
|
151
156
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
152
|
-
sglang/srt/layers/communicator.py,sha256=
|
153
|
-
sglang/srt/layers/dp_attention.py,sha256=
|
157
|
+
sglang/srt/layers/communicator.py,sha256=c5pJObNyP_7JsIWgLau_E-1ovtPCpAcge254fjo9Rqw,19988
|
158
|
+
sglang/srt/layers/dp_attention.py,sha256=tOre7il5Cppu930-tzM6d4AgjHuIJMCMlg9hJkuBcjA,11382
|
154
159
|
sglang/srt/layers/elementwise.py,sha256=MyQUflyKEfPZ-BggW1Kd4hB53RFD6FXGc2S5LXjx_do,16026
|
155
160
|
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=fkTcAB7qYwSWi95qI3Rqq0JUyDpJdcYkd4TYkWO01HI,5891
|
156
|
-
sglang/srt/layers/layernorm.py,sha256=
|
161
|
+
sglang/srt/layers/layernorm.py,sha256=Qkx4Jzb3KWOt2okAVM6Is4FDClpUIJShcPGoElUSnEQ,9598
|
157
162
|
sglang/srt/layers/linear.py,sha256=NzjLqZrZNYcc3z2KtA9-n6pnSdBHHwU6NF_BbcAWp48,52471
|
158
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
159
|
-
sglang/srt/layers/multimodal.py,sha256=
|
163
|
+
sglang/srt/layers/logits_processor.py,sha256=uduvaN1pFHX3imlx8FbmIG6aJMniOoPmoP0AGimQn5s,26630
|
164
|
+
sglang/srt/layers/multimodal.py,sha256=wVo5-OLz-J4k8fM0ld1ZKMtzOsSue4aa-uILak-I8Bk,2398
|
160
165
|
sglang/srt/layers/parameter.py,sha256=jCg0G-12GZqTa9gGOqEtVCsnnuBGnYg0VmF6pc6oCFg,17455
|
161
166
|
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
162
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
167
|
+
sglang/srt/layers/radix_attention.py,sha256=vtzCPfEiWYunglcLfqO9dcATb-LXzU4sFBwIWsWHbiY,3513
|
163
168
|
sglang/srt/layers/rotary_embedding.py,sha256=EhxI0E8jcTWZ2COpnku7crbW8Hew5fe_ujMndj7hKvE,52246
|
164
169
|
sglang/srt/layers/sampler.py,sha256=xNds1migup2s6b9_pS6ljkJUkvNtv7nmTGeIdOzoQ6w,11182
|
165
170
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
@@ -167,20 +172,21 @@ sglang/srt/layers/utils.py,sha256=IWGg1Hb7c33Z3LHRPVJyUAzp3BnSid23ZWXAmJ_Jvp8,12
|
|
167
172
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=FSAxHh1w9Qz4A2_8OQfIP5qsmq1s_g-Od-VLJ4vqQPw,22355
|
168
173
|
sglang/srt/layers/attention/aiter_backend.py,sha256=7sEUgViw-xl3yok91yyOD9gTi8lQmME0g0ZiKVTCcyI,32851
|
169
174
|
sglang/srt/layers/attention/ascend_backend.py,sha256=jPCsU9_gH1iZNoZHD9nCeDdVdXqBt31LI65N55BTJPg,8250
|
170
|
-
sglang/srt/layers/attention/base_attn_backend.py,sha256=
|
175
|
+
sglang/srt/layers/attention/base_attn_backend.py,sha256=_vM05ddWy6SaoqWYPR8w5lflSE4MhcVFR271Q9EKK8E,3600
|
171
176
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=SIR7sKCCegwzahSz82I3gsDyN5TkKoa4yG4-pBQWBi4,9813
|
172
177
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
173
178
|
sglang/srt/layers/attention/flashattention_backend.py,sha256=rYsBAsFS1qNNe-3CVIaXxWRqA3eul1jVQXvfZ_wlpwg,94076
|
174
179
|
sglang/srt/layers/attention/flashinfer_backend.py,sha256=HQp14R29hQVXYjATKPoGaHY9LJ9e1cw2k-RhBEmFxt8,51505
|
175
180
|
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=NirRlNFxD0S2EncvvmrerIxNfuTnYpvemZV3MR5_FnU,34040
|
176
181
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
182
|
+
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=ZIzBeR5r0SMkNLekEWPUCas_TCNOmzZ725YaueYVUlM,3196
|
177
183
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
178
184
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
179
185
|
sglang/srt/layers/attention/tbo_backend.py,sha256=CBnSDUmDvT-Tbhi9NHNo1LLkgUAcIsWMJgKa-sAIKW8,9318
|
180
186
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzbyKOWHAVPOD9b0n0dEehwlos,9496
|
181
187
|
sglang/srt/layers/attention/triton_backend.py,sha256=AryrPc4kzioxkiucPkApMA__0HoQTKOHNpwN0GEgm98,36923
|
182
188
|
sglang/srt/layers/attention/utils.py,sha256=KiRSIHaGBhErUhPWCSD3Uiaqb0pSEF0NJFwTTQXoMks,2887
|
183
|
-
sglang/srt/layers/attention/vision.py,sha256
|
189
|
+
sglang/srt/layers/attention/vision.py,sha256=zI1Pq2Tx4SwOzYhIarxNtlTiZeVMWxVf8j-Pf7xhzCA,18111
|
184
190
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=eN0Lqpu5h27lMPuRnisX4jrU0WR061pCFSrh3vLlSD0,18936
|
185
191
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
186
192
|
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=ImpCuxszoeVdr6wzaLR3OGW3-50P9EAEvsRCdUVIrxE,14261
|
@@ -192,15 +198,15 @@ sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNp
|
|
192
198
|
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=bc8s5Oc36pCF0VozxZuqFOOU2fov-4wGPlyduye3Imk,7296
|
193
199
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=SkOFgU23aZfHmLhnkVhdUWGx0-2wbo6uu9ohKBp2yOI,3486
|
194
200
|
sglang/srt/layers/moe/router.py,sha256=UrPieRvemN7Ew48gtG7DA2xhNDBRSnZxzugTEBI-0_E,12006
|
195
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
201
|
+
sglang/srt/layers/moe/topk.py,sha256=dOyJcpjIQYlgk8i_JsJyJzxaZZgmAcSMr9OgceG0arQ,26851
|
196
202
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
197
203
|
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=UFH-XacP3aBjAcn6_SeC641jGzjSrY0fz50IB9URix4,42706
|
198
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
204
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=6fspJli5_89rItBZDua_gNMP8eAq9ZgFOv029aoIIwg,45701
|
199
205
|
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=aiBE3mjvWV3eBrFGH9J44tuJncQwOjRS_XeyBNCEtqM,24379
|
200
206
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=4NXZHbCw-G-uSnNUj4up0yh3xBDPnT-x0pdoIr0lku8,831
|
201
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
202
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
203
|
-
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=
|
207
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=6NcY-6UHQUSVP4qzc8jis4h-W9BEV4lnGmrJMx2S6eA,57164
|
208
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=U3Qaffyj-aGFc6TvlB057eCbiv9oHbPDdwPVHsM7FJs,23278
|
209
|
+
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=HOEJJyehKTUIjkcsTc29aEXHqVLgDlv_jQL5fjvuUxU,5856
|
204
210
|
"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
|
205
211
|
"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
|
206
212
|
"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
|
@@ -345,6 +351,7 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=hoWVdf8ry8ID
|
|
345
351
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=pdQ1RvXvdWDn8Y8-8MAX3vn-T-wbtkZvHV9GZZvNjnc,3266
|
346
352
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
|
347
353
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
|
354
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=160,N=320,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=ZRON2XIRRZrvJ3tbPuQ7-0HqGZ_FkPpRN3yj1isGmpg,3255
|
348
355
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=ttFuL1rKnEpShItmlGyClOfpUwLi5cZYFaVgo7CAxnA,3268
|
349
356
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Pc2ri-qDByslfD8LgJtRB9QDWjI-KqMeA5ftltiwy8k,3262
|
350
357
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=uuua9V6-1H38ASMPQ60t7UOtV0IQLZWBCl13MwQ25Ss,3264
|
@@ -361,6 +368,7 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=hoWVdf8ry8ID
|
|
361
368
|
"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
|
362
369
|
"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
|
363
370
|
"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
|
371
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=320,device_name=NVIDIA_H20-3e.json",sha256=cWkEpNqnyn0QS8HcgWiwWI1xqh_U93_S1kyNeb69aOc,3238
|
364
372
|
"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
|
365
373
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=ENDYnC1ljPNpDVHdmqR7UbgDWT1IP_55ZIQ_Oae34mI,3264
|
366
374
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=5UAs8Z1myw8F-5FY2HHWd5WMT2ii9X-aYIYkf3FsA8s,3269
|
@@ -373,28 +381,28 @@ sglang/srt/layers/quantization/awq.py,sha256=gLEOx6QoGQ0McBEURXPVidKGsdNUjqc9sJw
|
|
373
381
|
sglang/srt/layers/quantization/awq_triton.py,sha256=4XwJbRNlFmlvjbMGtWF1Wvk26Kf96162vNEmuI5Kars,11737
|
374
382
|
sglang/srt/layers/quantization/base_config.py,sha256=CiSxG5iuOa-12V9kIOh0Fu8Y7knZxfFbbNGTo6nEaRE,7173
|
375
383
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=3avetVUBjCiuYWBJQbElbVXWpx0SgsFsDc5F9F_zHgA,13879
|
376
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
377
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
384
|
+
sglang/srt/layers/quantization/fp8.py,sha256=sIA-PCDDu2-AtcwvPcvzitxjCtrvEx_dig_AoocCfhY,47100
|
385
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=8alryD9sEROh9Dh4cdPrGIpuOPbT6Hx6PNSe8fJc9zM,40856
|
378
386
|
sglang/srt/layers/quantization/fp8_utils.py,sha256=6FVR6_Y8akP4ihCaGG_bLYurcC_PShPtiPgiEvGN5bE,25605
|
379
387
|
sglang/srt/layers/quantization/gptq.py,sha256=3q9xfq5sJJHcrVr9C8-l9JdcLFvwKAAfWJEfZW6CzLs,39145
|
380
388
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
381
389
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
382
390
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
383
391
|
sglang/srt/layers/quantization/marlin_utils.py,sha256=ShsoxcVTYo1Es3XKp9mlQNw-TsRF_o4mHIO5MfAP5HA,25906
|
384
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
392
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=pJDavvIiy6oY__GoknDgeq1o8jVF99CzYgWy7i6Cz9E,38288
|
385
393
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=NGcFjiMXwfOX10dkHAY3EgZHxox2k7I402Bvwj3jW1Q,19105
|
386
394
|
sglang/srt/layers/quantization/petit.py,sha256=74Jn0eICq23v_b4rEctDaYTINtbqkdM6IXycT-_FbbI,8954
|
387
395
|
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
388
396
|
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
389
397
|
sglang/srt/layers/quantization/scalar_type.py,sha256=nBk4THjeRWMGW3hKWRdrjfQ0gwpuBxmYqapDBaRpnr4,12395
|
390
|
-
sglang/srt/layers/quantization/unquant.py,sha256=
|
391
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
392
|
-
sglang/srt/layers/quantization/w4afp8.py,sha256=
|
398
|
+
sglang/srt/layers/quantization/unquant.py,sha256=zmxzCg46IOjIILRPFaZ4FPxodVT83X5nrFAKlkYUiVI,12330
|
399
|
+
sglang/srt/layers/quantization/utils.py,sha256=9ZmfS0MMqueQ6zIxMIFoQy2OFBQ5vHjOHBgVvUn7ews,16213
|
400
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=cYLUuDARPP6NsiYSihDnJYZwLakDL-RGYokTIJ-v_2I,11074
|
393
401
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=I_W9A4Pnluaf-SaT8zq-tAJTt1acpxfE_kG5mqdc5cE,10250
|
394
402
|
sglang/srt/layers/quantization/w8a8_int8.py,sha256=VGrVELArNuyw4FEtUefaeK8ayuX7cpXj1OOqCmOCzm4,34902
|
395
403
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
396
404
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=DsPCI82A4rqI6mjKo-WorIKUweppFV7-16Qku-zW9_g,25897
|
397
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
405
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=vwcgwGuPhH2kHBfg7DnsndzffrbZx8xuFsl9Qeegd9s,24286
|
398
406
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
399
407
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
400
408
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
@@ -559,8 +567,9 @@ sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=On_uvP1Thx
|
|
559
567
|
sglang/srt/lora/layers.py,sha256=FaTYf0w3zbKKKAT1nJdAzGRtxvySB6FpNKXvEi5RHH0,12958
|
560
568
|
sglang/srt/lora/lora.py,sha256=sRoU7BdlTV4cnBv1-u3QjisVR9XQrrqAsmhxdNtd8dU,9433
|
561
569
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
562
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
563
|
-
sglang/srt/lora/
|
570
|
+
sglang/srt/lora/lora_manager.py,sha256=ABuqg1IhY9LNXgJd_v3Yx_VHS52t4SapHmhLiH1thdc,20147
|
571
|
+
sglang/srt/lora/lora_registry.py,sha256=z3Ib7nlr1gajeSwJjC7sL8eMiaLiZo7dOB3WZnlyBVM,7676
|
572
|
+
sglang/srt/lora/mem_pool.py,sha256=UYvTgEPvBoVsaX5rEnipebOAlo75pML6_NO9GfCFzl8,12148
|
564
573
|
sglang/srt/lora/utils.py,sha256=5G0KiDEn-Zg4OgIOjWnU2ZdQGNstZswoAog9xU4GVDA,5660
|
565
574
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
566
575
|
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
@@ -570,39 +579,39 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVh
|
|
570
579
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=iz5scFNo2YFTeiM8beWg9Z1oZI-6AM_T1wBMCQ6qp2Q,6485
|
571
580
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
572
581
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
573
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
582
|
+
sglang/srt/managers/cache_controller.py,sha256=HoI6_os2h8rrvyEJ6Kk4ibUF3aKH-9Z8K5pksc6BECQ,24603
|
574
583
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
575
584
|
sglang/srt/managers/data_parallel_controller.py,sha256=PZ-wOcAFn3PQqMB6I2vjIsFmplf0nlNl5hqTDKTHTG8,12112
|
576
585
|
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
577
|
-
sglang/srt/managers/io_struct.py,sha256=
|
578
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
579
|
-
sglang/srt/managers/multimodal_processor.py,sha256=
|
580
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
586
|
+
sglang/srt/managers/io_struct.py,sha256=LNLG7utMidF63eYWlWYxQ3G2GzOqaQzQc-9ld2yaycI,37859
|
587
|
+
sglang/srt/managers/mm_utils.py,sha256=VrJiv0k_zDa83BsfVv8rmckgXKsvF0Wz88bCAb6R1as,29601
|
588
|
+
sglang/srt/managers/multimodal_processor.py,sha256=mLnGcUHIvjruwoVhqiz4j7RMYMsZnvQMH8JnKCITDlY,1805
|
589
|
+
sglang/srt/managers/schedule_batch.py,sha256=xmWSPAsllmPaWtKNrf-P8IX6fuQMTD-vZuk1y01vUjA,76289
|
581
590
|
sglang/srt/managers/schedule_policy.py,sha256=BFYItMXtrsO5157tpFhYwLpZ8NSlzR4_gNZC1iE10D4,22400
|
582
|
-
sglang/srt/managers/scheduler.py,sha256=
|
591
|
+
sglang/srt/managers/scheduler.py,sha256=rwI-qSIeVkzxkmVXPPtbK0mkQ5WY3myU3lV_AImFJ-Y,122502
|
583
592
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=Ei-9lyfrSQAlL9_ULuJLAhA7qpvUzjsBDzBBTDdnt4Q,31394
|
584
593
|
sglang/srt/managers/session_controller.py,sha256=dzlMNZlo20FTSl64QqK7y7pElsdCy8ICOWWBPTBVwgs,6040
|
585
594
|
sglang/srt/managers/template_manager.py,sha256=RrwRA2oqId_PMQ98qJQGwIxMroOxiorl2sGC9ARou_0,8543
|
586
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
587
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
595
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=yAgnR5eYeiid8gwJSBNQ1tkrYd5dq0RHXWn8nO_UdvY,76284
|
596
|
+
sglang/srt/managers/tp_worker.py,sha256=D_NoiX69ry8cKRUYjX4nhtlPLdz1dipJEJekTouNG70,11363
|
588
597
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=kK0pn8mz-XgLGvVlJK6LvDVp4lnFk5vJH-Cs9NQ5Un4,10959
|
589
598
|
sglang/srt/managers/utils.py,sha256=9_VGE48EK0PXVJ26aYvbRJ6n7gIZALvCcf6uZCccCgM,1369
|
590
|
-
sglang/srt/mem_cache/allocator.py,sha256=
|
599
|
+
sglang/srt/mem_cache/allocator.py,sha256=id4riucsG9d-P1ikj3-DLJbzhM8-MuJfvDmB8H4g9-o,23364
|
591
600
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=hLS2ncTMAz7Kpdk5pNwn5c6g8b61_K9OCBL4Vj1xsYc,2801
|
592
601
|
sglang/srt/mem_cache/chunk_cache.py,sha256=FU_fq8e_dodgU8EkRqE4Jr0sKwCXQnKmapO88k6_JfU,3207
|
593
602
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
594
|
-
sglang/srt/mem_cache/hicache_storage.py,sha256=
|
595
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
603
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=pvNeooVmCZBeZFgSHWNGPZzqtHI_qJ5BpTy_A4i6gg8,5539
|
604
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=3BXlIZUyQk2dkwuwsMvSUSXd8fCDLPvcTLOp9FnzxBY,24779
|
596
605
|
sglang/srt/mem_cache/memory_pool.py,sha256=jQdWgOr6hpMLbGaEJc4immBgZG_MZbx8LyOv029ASVw,40932
|
597
|
-
sglang/srt/mem_cache/memory_pool_host.py,sha256=
|
606
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=xcjYyC94FOH_NguWbLUG4vF_CSBcxA_msuRsBasYCPo,10387
|
598
607
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=wZl2KeEl3xeoEsYdH33UoM-FO8kqfLo_XUgereJVvoM,1348
|
599
608
|
sglang/srt/mem_cache/radix_cache.py,sha256=kp4JiVxh3eS4MsFxGKIYjYAb14B777qc1bHrABPqBMc,19101
|
600
609
|
sglang/srt/mem_cache/swa_radix_cache.py,sha256=4qt_gS7GuHiekd6VvKkx54dB2GHJzNA_kj71Np6jTDA,40300
|
601
610
|
sglang/srt/metrics/collector.py,sha256=FH6Wil2lMK7d7q74CfxfdULCaHKDXeAoo8UBZqqdepM,20289
|
602
611
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
603
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
604
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
605
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
612
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=6njRGysrhBDi2bAt5DyjGnyrexYvuEVsAJwQBBW8Ut0,31886
|
613
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=NvUhReevoy6UfO4991P_5MPQyfefC3BOoTwTqUwMbYk,38430
|
614
|
+
sglang/srt/model_executor/model_runner.py,sha256=UkI7i73Noaar9__sYVDGA-xEQHYSllZPUxRIbLwduWU,72373
|
606
615
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
607
616
|
sglang/srt/model_loader/loader.py,sha256=wxSUYrqv23w9yHYy9Lm0ozWggs9pf6Co4yqe1UO8PZk,59799
|
608
617
|
sglang/srt/model_loader/utils.py,sha256=svSrPQxViBz_-0_sByu4coCYrzJ51-4FCi_bFqa6rDo,4474
|
@@ -616,7 +625,7 @@ sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,155
|
|
616
625
|
sglang/srt/models/deepseek.py,sha256=sqobTr9a9c5pNLNJZE-WrJIE_qBq0lC5gCGv9NpGU_Q,17364
|
617
626
|
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
618
627
|
sglang/srt/models/deepseek_nextn.py,sha256=47fehxRdiOizr0rdLg5f1fzQEx6gGAOcDcWKtblloyk,5928
|
619
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
628
|
+
sglang/srt/models/deepseek_v2.py,sha256=d6itbiEH_Zj0DdvH10dbxwTN7kK4g7rQYJVQ6A2-B70,105428
|
620
629
|
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
621
630
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
622
631
|
sglang/srt/models/gemma.py,sha256=2atKwFN5wCsJCmBRmURX9vaCcFjxlFirL7xsnG5KPlI,14180
|
@@ -628,6 +637,8 @@ sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnL
|
|
628
637
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
629
638
|
sglang/srt/models/gemma3n_mm.py,sha256=pL_fvnkz9fKaC2Afms5KG3Me3u5sp1C2-mAUhqPGrQ4,18701
|
630
639
|
sglang/srt/models/glm4.py,sha256=2VQzUqFkQTy_2nfkxP9SF6_9kKLTZUExGRjge7r99Es,11265
|
640
|
+
sglang/srt/models/glm4_moe.py,sha256=vNJfab2DVhMEU-9RsPd7zyLofkX7SqYHRY97vFcYkDA,39864
|
641
|
+
sglang/srt/models/glm4_moe_nextn.py,sha256=cWB6o3w7xBvgi2ouGKsqZ3iovKH65QiRQul42wcgzMk,5897
|
631
642
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
632
643
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
633
644
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
@@ -637,7 +648,8 @@ sglang/srt/models/hunyuan.py,sha256=GVDeMKgcqW6HMFWPUukznL5JoDW4CpOpS5Q_PXlbHw8,
|
|
637
648
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
638
649
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
639
650
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
640
|
-
sglang/srt/models/
|
651
|
+
sglang/srt/models/interns1.py,sha256=nResXUzfcHZoJie1gHuYwyVir7Ys2fWp3hjzTs6Utvk,14182
|
652
|
+
sglang/srt/models/internvl.py,sha256=o6XSAvnMYK5tTPbln9RI9BfRfAQZBE8_xmGPffrznnQ,27838
|
641
653
|
sglang/srt/models/kimi_vl.py,sha256=XulRiufQzOSWZe8-bUl2OEdznvsVU9OBsEYipaX3YkM,12877
|
642
654
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
643
655
|
sglang/srt/models/llama.py,sha256=Nsxv2s1sOmLnZsTHkwbTh53cUFEQ2fnKDQi5BFbFcsk,28994
|
@@ -647,19 +659,19 @@ sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkE
|
|
647
659
|
sglang/srt/models/llama_eagle3.py,sha256=715soylDE3kOMWskbPy_70BFxaSc5ptaHCS1v3-ViA0,8579
|
648
660
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
649
661
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
650
|
-
sglang/srt/models/llava.py,sha256=
|
662
|
+
sglang/srt/models/llava.py,sha256=xzYip_BAwpzSIdZre43LZiyTpFISa0ZCLdO6LUSbaCg,37702
|
651
663
|
sglang/srt/models/llavavid.py,sha256=-CSk0RJ2MQeb81sh-RISeVJFaI-XWY6nR6_I594MkME,12818
|
652
664
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
653
665
|
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
654
666
|
sglang/srt/models/minicpm.py,sha256=CzBJyZtfMpp8jvlEl29DHI7HLVq-CxuqP1UHwxIbaUI,14567
|
655
667
|
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
656
|
-
sglang/srt/models/minicpmo.py,sha256=
|
668
|
+
sglang/srt/models/minicpmo.py,sha256=st8I13Ere5RkRHHQQN1LgZh1ybUA3_buxaaE4XlV8ag,76123
|
657
669
|
sglang/srt/models/minicpmv.py,sha256=g4aAOG8PVGkZqGmlneVaScAtNpSLqSVbZGRAikyrBy8,30394
|
658
670
|
sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,3475
|
659
671
|
sglang/srt/models/mixtral.py,sha256=j2whKt4GdQqtpKL5iN0Vb4TO4el1E2qEpUCI57E_47Q,17222
|
660
672
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
661
673
|
sglang/srt/models/mllama.py,sha256=OdX7brhyfGiMFPulxF77QOUi-Kcscg3Qo4ipyxzs9yA,39670
|
662
|
-
sglang/srt/models/mllama4.py,sha256=
|
674
|
+
sglang/srt/models/mllama4.py,sha256=yt2YNE7S6buLAaqSfxD2LcJL1ZRzUzKWU21rCbzDzQo,20465
|
663
675
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
664
676
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
665
677
|
sglang/srt/models/olmoe.py,sha256=WdPtyKsd3u8OpVsXmDwWuVpt1gTF0679IRkc1pvfnMM,16040
|
@@ -677,11 +689,11 @@ sglang/srt/models/qwen2_5_vl.py,sha256=vOuIyK_NLuGgz9LlAdyM7cSQUU93VnBCYXUr_n4iO
|
|
677
689
|
sglang/srt/models/qwen2_audio.py,sha256=lVeYmC29eVZIR9I6ZjFe4xvC0wSXR0NtGCli6fSXtms,7870
|
678
690
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
679
691
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
680
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
692
|
+
sglang/srt/models/qwen2_moe.py,sha256=drTwlJlP0PLDl-Rl2h4GaOmOxexV1SMjMP97izhVpLk,25822
|
681
693
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
682
694
|
sglang/srt/models/qwen2_vl.py,sha256=ZRAL32Ymt4ZCBqB0JorXAm4ZBrECZ9EbaXKaTSikkQM,21366
|
683
695
|
sglang/srt/models/qwen3.py,sha256=COSC1TsCQNTq3E1QoVJYj1yTn-CFEVEX7keRwrrBXLs,20121
|
684
|
-
sglang/srt/models/qwen3_moe.py,sha256=
|
696
|
+
sglang/srt/models/qwen3_moe.py,sha256=Vcdt77gDniDoZiAgsdhcWHtw1GiH-3Pk8GpiUxpjXWc,34019
|
685
697
|
sglang/srt/models/registry.py,sha256=bH9H0OiNV0Cn7FRBM30Oh6dxICTs9mJscdLtHYPJvxc,3783
|
686
698
|
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
687
699
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
@@ -693,25 +705,25 @@ sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,1
|
|
693
705
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
694
706
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
695
707
|
sglang/srt/multimodal/mm_utils.py,sha256=6bV1_a7Iet9W0y3qdd0E-hFM78zalIzNZCYbLzJX2y8,12640
|
696
|
-
sglang/srt/multimodal/processors/base_processor.py,sha256=
|
697
|
-
sglang/srt/multimodal/processors/clip.py,sha256=
|
698
|
-
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=
|
699
|
-
sglang/srt/multimodal/processors/gemma3.py,sha256=
|
700
|
-
sglang/srt/multimodal/processors/gemma3n.py,sha256=
|
701
|
-
sglang/srt/multimodal/processors/internvl.py,sha256=
|
702
|
-
sglang/srt/multimodal/processors/janus_pro.py,sha256=
|
703
|
-
sglang/srt/multimodal/processors/kimi_vl.py,sha256=
|
704
|
-
sglang/srt/multimodal/processors/llava.py,sha256=
|
705
|
-
sglang/srt/multimodal/processors/minicpm.py,sha256=
|
706
|
-
sglang/srt/multimodal/processors/mlama.py,sha256=
|
707
|
-
sglang/srt/multimodal/processors/mllama4.py,sha256=
|
708
|
-
sglang/srt/multimodal/processors/phi4mm.py,sha256=
|
709
|
-
sglang/srt/multimodal/processors/pixtral.py,sha256=
|
710
|
-
sglang/srt/multimodal/processors/qwen_audio.py,sha256=
|
711
|
-
sglang/srt/multimodal/processors/qwen_vl.py,sha256=
|
712
|
-
sglang/srt/multimodal/processors/vila.py,sha256=
|
708
|
+
sglang/srt/multimodal/processors/base_processor.py,sha256=duDeCOOeXRt8lYi34fCe40Gezz0-Ao-rN9Zenx8p4c8,24430
|
709
|
+
sglang/srt/multimodal/processors/clip.py,sha256=5nXZuQYbyf-5mlqPwjhQrlWqxvswImWZQXivChsiHfQ,1057
|
710
|
+
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=Pymag9f0U5L_bBOTFs2q94BbuPJ-VwqSixs3meO0nsM,2569
|
711
|
+
sglang/srt/multimodal/processors/gemma3.py,sha256=7aD6cR60iSC_MqjzdCDMAgtrb_cmy9YJyqLgVRClBT8,1986
|
712
|
+
sglang/srt/multimodal/processors/gemma3n.py,sha256=zml4ovgDzgFZxupnsTfmGtT69ymY_eY0Zp3hR6TkBY0,3056
|
713
|
+
sglang/srt/multimodal/processors/internvl.py,sha256=p8dba1LBEceGObJvPdq3auDhlMKQIXyp_fXM5VMd4BI,9771
|
714
|
+
sglang/srt/multimodal/processors/janus_pro.py,sha256=_4ltWmdtFjbh1VCMRbcgxW61eWIABIzHG-YgwHWaYq8,1471
|
715
|
+
sglang/srt/multimodal/processors/kimi_vl.py,sha256=5i8KmGxnnDtQc7XqUBNyanAfGxhxj8iRFBFONHmpiFg,1565
|
716
|
+
sglang/srt/multimodal/processors/llava.py,sha256=1pb47tlbgH8IUgxTb2YFsK87-x16xmC6BZFHc5r2x9g,8097
|
717
|
+
sglang/srt/multimodal/processors/minicpm.py,sha256=ysJlUaxcBcWjKliz5VmXKVv0ec4QWRHXZk4ga-hXVf0,5354
|
718
|
+
sglang/srt/multimodal/processors/mlama.py,sha256=FgPm2JQzfPFDcGYDm0mqfDfO_eJKy-NiVgF-vId6w8Y,1233
|
719
|
+
sglang/srt/multimodal/processors/mllama4.py,sha256=1YGETKSzMZIa7BOwq3T9cbsYjUcW5sopcpc9JNJ000g,1911
|
720
|
+
sglang/srt/multimodal/processors/phi4mm.py,sha256=8GaUVpGucV4UKoa0XkxN0gDpMZax6UyCiRBX_QaJK78,3857
|
721
|
+
sglang/srt/multimodal/processors/pixtral.py,sha256=Lx5Z-9NkovLDTHlRBznHxGn4r2XhDz8am2XpOskOVQY,3203
|
722
|
+
sglang/srt/multimodal/processors/qwen_audio.py,sha256=jxtArfNuBH4q9LQVEydMDsj85avqBGNl-v1ZZTjC9E0,2367
|
723
|
+
sglang/srt/multimodal/processors/qwen_vl.py,sha256=tZOpz8dabyNvjS4hn0UxLf-EaEZH8kmHjyZaYRm9EZ8,10498
|
724
|
+
sglang/srt/multimodal/processors/vila.py,sha256=vWgV1lTdjiFiTR8w-7fC66-L_tpOOD59c-c9NljGelE,2192
|
713
725
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
714
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
726
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=Duk4Fp99QZyOFld3i4AGwkW9FlULY86CNKv6v0_kA4w,14683
|
715
727
|
sglang/srt/sampling/sampling_params.py,sha256=HbVcCeSXgPW19MRB-v0FTG1D-zHDAY6-toxyndSl-zI,6462
|
716
728
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
717
729
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
@@ -719,16 +731,17 @@ sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4T
|
|
719
731
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
720
732
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
721
733
|
sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18nst2oOD8HnA2mZ4,12859
|
722
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
723
|
-
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=
|
724
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
725
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
734
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=kVqMGj25jxtJlP-nTSlq_QJgoabFqKOU7-0WeUFhvw8,14509
|
735
|
+
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=hLjaD66K3ZE5SWsjvSiSdSexQ55F3EuSnfb4oe7rrSY,15261
|
736
|
+
sglang/srt/speculative/eagle_utils.py,sha256=x5MKA2GkecNAXE58KKhPJRy5KxCLhRkD-C_kVSZIyzc,46433
|
737
|
+
sglang/srt/speculative/eagle_worker.py,sha256=8yPQZxpBvcr--Ooo4nov3LqzkLRL-GOLJlwu91wMAmQ,38650
|
726
738
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
739
|
+
sglang/srt/weight_sync/utils.py,sha256=jpmfXtiCvUYpwWh4bMgQgv0JSulPi8TwIz4aTsxi0XU,4148
|
727
740
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
728
741
|
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
729
742
|
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
730
743
|
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
731
|
-
sglang/test/runners.py,sha256=
|
744
|
+
sglang/test/runners.py,sha256=q01InkXESqxZe19NeH5SzK11HuQG13gFEfm3N7XAIpU,33714
|
732
745
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
733
746
|
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
734
747
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
@@ -736,7 +749,7 @@ sglang/test/simple_eval_humaneval.py,sha256=s8YuKIBkNUEOBP4XKsTMRdXGv5aRhl0oJyl-
|
|
736
749
|
sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
|
737
750
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
738
751
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
739
|
-
sglang/test/test_activation.py,sha256=
|
752
|
+
sglang/test/test_activation.py,sha256=bDBFl4Y30siXj7Ifl66fc2HytOrcZdHFiP2i9K8TIsY,3140
|
740
753
|
sglang/test/test_block_fp8.py,sha256=hd3GXuC_wxn0HGAN3KCs6Nxf98AHO8XaRvGsvWS-CHc,21822
|
741
754
|
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
742
755
|
sglang/test/test_block_fp8_ep.py,sha256=XGZEs7cJiLjatRZcdcav4aFIQxnQB8Vq-b3HmAsw-Ww,10859
|
@@ -750,13 +763,13 @@ sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg
|
|
750
763
|
sglang/test/test_marlin_moe.py,sha256=PITMGcGF4ci2csXJejdLSNuxpURnFmcflsipAZsGakU,7991
|
751
764
|
sglang/test/test_marlin_utils.py,sha256=gFMJwxbfEEJDeHI-HU5FDF9FFqqcM-yahK0TWyVIVgQ,5171
|
752
765
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
753
|
-
sglang/test/test_utils.py,sha256=
|
766
|
+
sglang/test/test_utils.py,sha256=hnT1lvTERIpmTapJKttFPfZCqHjNsTqiWNqpn5r-6CU,39454
|
754
767
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
755
768
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
756
769
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
757
770
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
758
|
-
sglang-0.4.9.
|
759
|
-
sglang-0.4.9.
|
760
|
-
sglang-0.4.9.
|
761
|
-
sglang-0.4.9.
|
762
|
-
sglang-0.4.9.
|
771
|
+
sglang-0.4.9.post5.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
772
|
+
sglang-0.4.9.post5.dist-info/METADATA,sha256=jv_hoxV9ahzQ3tRZRibHpMxmYK6-lCJUDCd09LK4dPU,27348
|
773
|
+
sglang-0.4.9.post5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
774
|
+
sglang-0.4.9.post5.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
775
|
+
sglang-0.4.9.post5.dist-info/RECORD,,
|