sglang 0.5.3__py3-none-any.whl → 0.5.3.post1__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 +0 -2
- sglang/bench_serving.py +224 -127
- sglang/compile_deep_gemm.py +3 -0
- sglang/launch_server.py +0 -14
- sglang/srt/configs/__init__.py +2 -0
- sglang/srt/configs/falcon_h1.py +12 -58
- sglang/srt/configs/mamba_utils.py +117 -0
- sglang/srt/configs/model_config.py +68 -31
- sglang/srt/configs/nemotron_h.py +286 -0
- sglang/srt/configs/qwen3_next.py +11 -43
- sglang/srt/disaggregation/decode.py +7 -18
- sglang/srt/disaggregation/decode_kvcache_offload_manager.py +1 -1
- sglang/srt/disaggregation/nixl/conn.py +55 -23
- sglang/srt/disaggregation/prefill.py +17 -32
- sglang/srt/entrypoints/engine.py +2 -2
- sglang/srt/entrypoints/grpc_request_manager.py +10 -23
- sglang/srt/entrypoints/grpc_server.py +220 -80
- sglang/srt/entrypoints/http_server.py +49 -1
- sglang/srt/entrypoints/openai/protocol.py +159 -31
- sglang/srt/entrypoints/openai/serving_chat.py +13 -71
- sglang/srt/entrypoints/openai/serving_tokenize.py +144 -0
- sglang/srt/environ.py +4 -0
- sglang/srt/function_call/function_call_parser.py +8 -6
- sglang/srt/grpc/sglang_scheduler_pb2.py +78 -70
- sglang/srt/grpc/sglang_scheduler_pb2.pyi +64 -6
- sglang/srt/grpc/sglang_scheduler_pb2_grpc.py +88 -0
- sglang/srt/layers/attention/attention_registry.py +31 -22
- sglang/srt/layers/attention/fla/layernorm_gated.py +47 -30
- sglang/srt/layers/attention/flashattention_backend.py +0 -1
- sglang/srt/layers/attention/flashinfer_backend.py +223 -6
- sglang/srt/layers/attention/flashinfer_mla_backend.py +1 -1
- sglang/srt/layers/attention/hybrid_linear_attn_backend.py +165 -59
- sglang/srt/layers/attention/mamba/causal_conv1d.py +1 -1
- sglang/srt/layers/attention/mamba/causal_conv1d_triton.py +9 -4
- sglang/srt/layers/attention/mamba/mamba.py +189 -241
- sglang/srt/layers/attention/mamba/mamba2_metadata.py +211 -0
- sglang/srt/layers/attention/mamba/mixer2_rms_norm_gated.py +120 -0
- sglang/srt/layers/attention/mamba/ops/ssd_bmm.py +0 -50
- sglang/srt/layers/attention/mamba/ops/ssd_chunk_scan.py +0 -60
- sglang/srt/layers/attention/mamba/ops/ssd_chunk_state.py +0 -111
- sglang/srt/layers/attention/mamba/ops/ssd_state_passing.py +0 -11
- sglang/srt/layers/attention/triton_backend.py +1 -1
- sglang/srt/layers/logits_processor.py +136 -6
- sglang/srt/layers/modelopt_utils.py +11 -0
- sglang/srt/layers/moe/cutlass_w4a8_moe.py +18 -21
- sglang/srt/layers/moe/ep_moe/kernels.py +31 -452
- sglang/srt/layers/moe/ep_moe/layer.py +8 -286
- sglang/srt/layers/moe/fused_moe_triton/layer.py +6 -11
- sglang/srt/layers/moe/moe_runner/deep_gemm.py +304 -0
- sglang/srt/layers/moe/moe_runner/runner.py +3 -0
- sglang/srt/layers/moe/utils.py +7 -1
- sglang/srt/layers/quantization/__init__.py +1 -1
- sglang/srt/layers/quantization/fp8.py +84 -18
- sglang/srt/layers/quantization/modelopt_quant.py +1 -1
- sglang/srt/layers/quantization/quark/quark.py +3 -1
- sglang/srt/layers/quantization/w4afp8.py +2 -16
- sglang/srt/lora/lora_manager.py +0 -8
- sglang/srt/managers/overlap_utils.py +18 -16
- sglang/srt/managers/schedule_batch.py +119 -90
- sglang/srt/managers/schedule_policy.py +1 -1
- sglang/srt/managers/scheduler.py +213 -126
- sglang/srt/managers/scheduler_metrics_mixin.py +1 -1
- sglang/srt/managers/scheduler_output_processor_mixin.py +180 -86
- sglang/srt/managers/tokenizer_manager.py +270 -53
- sglang/srt/managers/tp_worker.py +39 -28
- sglang/srt/mem_cache/allocator.py +7 -2
- sglang/srt/mem_cache/chunk_cache.py +1 -1
- sglang/srt/mem_cache/memory_pool.py +162 -68
- sglang/srt/mem_cache/radix_cache.py +8 -3
- sglang/srt/mem_cache/swa_radix_cache.py +70 -14
- sglang/srt/model_executor/cuda_graph_runner.py +1 -1
- sglang/srt/model_executor/forward_batch_info.py +4 -18
- sglang/srt/model_executor/model_runner.py +55 -51
- sglang/srt/model_loader/__init__.py +1 -1
- sglang/srt/model_loader/loader.py +187 -6
- sglang/srt/model_loader/weight_utils.py +3 -0
- sglang/srt/models/falcon_h1.py +11 -9
- sglang/srt/models/gemma3_mm.py +16 -0
- sglang/srt/models/grok.py +5 -13
- sglang/srt/models/mixtral.py +1 -3
- sglang/srt/models/mllama4.py +11 -1
- sglang/srt/models/nemotron_h.py +514 -0
- sglang/srt/models/utils.py +5 -1
- sglang/srt/sampling/sampling_batch_info.py +11 -9
- sglang/srt/server_args.py +100 -33
- sglang/srt/speculative/eagle_worker.py +11 -13
- sglang/srt/speculative/ngram_worker.py +12 -11
- sglang/srt/speculative/spec_utils.py +0 -1
- sglang/srt/two_batch_overlap.py +1 -0
- sglang/srt/utils/common.py +18 -0
- sglang/srt/utils/hf_transformers_utils.py +2 -0
- sglang/test/longbench_v2/__init__.py +1 -0
- sglang/test/longbench_v2/test_longbench_v2_eval.py +238 -0
- sglang/test/longbench_v2/validate_longbench_v2.py +337 -0
- sglang/test/longbench_v2/validate_longbench_v2_standalone.py +306 -0
- sglang/test/run_eval.py +40 -0
- sglang/test/simple_eval_longbench_v2.py +332 -0
- sglang/test/test_cutlass_w4a8_moe.py +9 -19
- sglang/test/test_deterministic.py +18 -2
- sglang/test/test_deterministic_utils.py +81 -0
- sglang/test/test_disaggregation_utils.py +63 -0
- sglang/test/test_utils.py +32 -11
- sglang/version.py +1 -1
- {sglang-0.5.3.dist-info → sglang-0.5.3.post1.dist-info}/METADATA +4 -4
- {sglang-0.5.3.dist-info → sglang-0.5.3.post1.dist-info}/RECORD +109 -98
- sglang/srt/layers/attention/mamba/mamba_utils.py +0 -81
- sglang/srt/managers/tp_worker_overlap_thread.py +0 -311
- sglang/test/test_block_fp8_ep.py +0 -358
- /sglang/srt/speculative/{ngram_utils.py → ngram_info.py} +0 -0
- {sglang-0.5.3.dist-info → sglang-0.5.3.post1.dist-info}/WHEEL +0 -0
- {sglang-0.5.3.dist-info → sglang-0.5.3.post1.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.5.3.dist-info → sglang-0.5.3.post1.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=
|
3
|
+
sglang/bench_one_batch.py,sha256=Z3qV8Gql0SjNlp_u64-_7S4rnsQRXKFIgc_Xv0wMM3E,23045
|
4
4
|
sglang/bench_one_batch_server.py,sha256=nD7GMOQE1I57BC1E7dTmqx-PMeSUPq8RF8W39s5z86I,26128
|
5
|
-
sglang/bench_serving.py,sha256=
|
5
|
+
sglang/bench_serving.py,sha256=NcsYVzCuB3g12S8gLtLENPhTlV7jPYnvNC3AOORmK7Q,90484
|
6
6
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
7
|
-
sglang/compile_deep_gemm.py,sha256=
|
7
|
+
sglang/compile_deep_gemm.py,sha256=ofuci3hhuWW3akUhI4EInPUU0AQgRNz2oWmC9KsA4dU,6582
|
8
8
|
sglang/global_config.py,sha256=qnMsK6AKzl8dhEbg-Jlbp_OVY9JUV0X9BqQiOl8VkiE,1737
|
9
|
-
sglang/launch_server.py,sha256=
|
9
|
+
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
10
10
|
sglang/profiler.py,sha256=zjD9-TxnDv3yU1Qmv4vItH5Nuhiu230ssqOA43EyH2g,4420
|
11
11
|
sglang/utils.py,sha256=YreOyt4-fWdDcg01abaMJ0y0ly4gYps26vRlmWhwGC8,17267
|
12
|
-
sglang/version.py,sha256=
|
12
|
+
sglang/version.py,sha256=vAhdketIKWmjUuWZ8PfKJlRx4zq5ctgCLf0t58Wuui0,28
|
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
|
@@ -30,20 +30,20 @@ sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
|
30
30
|
sglang/srt/bench_utils.py,sha256=zNTsTBUta27XxojgvR5p5X9M0v1MFzZ7dcX9TMq4NvQ,4348
|
31
31
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
32
32
|
sglang/srt/custom_op.py,sha256=m5F7x3LHlnOuesmcNmJtIWsfHGFLBJ807vKc05Gu1D0,3312
|
33
|
-
sglang/srt/environ.py,sha256=
|
33
|
+
sglang/srt/environ.py,sha256=vjqtjGpcO9svAQMHrGL4T0cLZW5izTErRFXU30ngiZQ,9029
|
34
34
|
sglang/srt/host_shared_memory.py,sha256=00TgVm3PNCl4rTPJZChG5uu4I5hd_Xf587r39tibmIg,2274
|
35
35
|
sglang/srt/offloader.py,sha256=cYON5jZErAp88Sh5JseaRw0B2Ho2MQz9smgvrTc-2KA,18765
|
36
36
|
sglang/srt/operations.py,sha256=za_h1_kcR1Te6-i_r0i_zAeumbmIRhLK2pS31sukkrw,6089
|
37
37
|
sglang/srt/operations_strategy.py,sha256=-w6GI2VgSGvORy3pUWRAJo6244ykSW1ZBV1Dx0fZlHA,7138
|
38
|
-
sglang/srt/server_args.py,sha256=
|
38
|
+
sglang/srt/server_args.py,sha256=dlT7Z2X8a4UWYZUPvyoXjL7BSB2DiyZuMNg394wCEtk,141412
|
39
39
|
sglang/srt/server_args_config_parser.py,sha256=niM5LYNaVxQg4FKHUJ3YmMZ-ekB3bDlvTwD7KqdLZoE,5220
|
40
40
|
sglang/srt/single_batch_overlap.py,sha256=m70hHl1ufIvc_9Nl2bYqnIcfoMIJkPyGjWIqJLBsKhI,4844
|
41
41
|
sglang/srt/torch_memory_saver_adapter.py,sha256=WFwPsOBvnWu6N2yTHmiOjLbDAYosslHwNSfyFHjz-7w,2511
|
42
|
-
sglang/srt/two_batch_overlap.py,sha256=
|
42
|
+
sglang/srt/two_batch_overlap.py,sha256=i34Ln_cwZsoLpSpYDVeqyqyat8cs1UD2rSYBsxOaQjI,34271
|
43
43
|
sglang/srt/warmup.py,sha256=fQYzNp-I9mZccs2BerI6mOZd1CDQjdiuFCeUkcwiOb4,1834
|
44
44
|
sglang/srt/batch_invariant_ops/__init__.py,sha256=Z9TvOE4BL7cAaBIePEsVglH7RcWBSBIsSHs-XbveQNE,728
|
45
45
|
sglang/srt/batch_invariant_ops/batch_invariant_ops.py,sha256=5vtvEFezea4tjGFuVMkadgZxynxAZZ8yxGwpkSm7Sl4,16246
|
46
|
-
sglang/srt/configs/__init__.py,sha256=
|
46
|
+
sglang/srt/configs/__init__.py,sha256=0PLismnlAj4zifXEbPJ_BphfbYxP32p-qXZ7P1o67PY,1223
|
47
47
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
48
48
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
49
49
|
sglang/srt/configs/deepseekvl2.py,sha256=sYMmoy5_LlDXht7MTi4QGYOaiE8iMGUO44bnuOu4i8I,23683
|
@@ -51,15 +51,17 @@ sglang/srt/configs/device_config.py,sha256=1Iaxrk65bJsCWV3E2cDfiap_T_xJIIj9oFVn9
|
|
51
51
|
sglang/srt/configs/dots_ocr.py,sha256=HSKerqzHzrKIzoNZOUXA_KiBLmL-Rs8h4Vw17pjF1Uo,1863
|
52
52
|
sglang/srt/configs/dots_vlm.py,sha256=PYoSrT-sRoykfNhdXFauqv21Sb54iavjYD3F09xww3U,5176
|
53
53
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
54
|
-
sglang/srt/configs/falcon_h1.py,sha256=
|
54
|
+
sglang/srt/configs/falcon_h1.py,sha256=564K7eOya-Ndb8HlQSke9zydmgUSvR-JZtlpWhpf_zE,15055
|
55
55
|
sglang/srt/configs/internvl.py,sha256=rIC-CBWJHy-Mjmk0_H3YcvVmZzeCRbXGo3dQMex-yeg,28141
|
56
56
|
sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsrKI,19156
|
57
57
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
58
58
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
59
59
|
sglang/srt/configs/load_config.py,sha256=_XhZdoP2Kbzih3FBZiiwGhXBf2-bNrn6f8eA63zqS7Y,3840
|
60
60
|
sglang/srt/configs/longcat_flash.py,sha256=Qp25xJVLq2K72Z80cXhcJxtqhagAdiPySDoevuT0Sno,3589
|
61
|
-
sglang/srt/configs/
|
62
|
-
sglang/srt/configs/
|
61
|
+
sglang/srt/configs/mamba_utils.py,sha256=yTLrrZ5-KaLz1mi6WPwKzitOBkZFvcUwUcfNOeTohPc,3706
|
62
|
+
sglang/srt/configs/model_config.py,sha256=miYOrW8VYnoybcJL_blKZXtbKMpsA6ADvegdECS8438,36870
|
63
|
+
sglang/srt/configs/nemotron_h.py,sha256=X39hWm2KQoAcZ4HXKDCfbua9aOTlcxcK89c52cmAq-k,13072
|
64
|
+
sglang/srt/configs/qwen3_next.py,sha256=K1uNLTypM7bfsZPxBYyu93WuwGNs9MG3qnliycCRynk,15013
|
63
65
|
sglang/srt/configs/qwen3_vl.py,sha256=FMC-SVeM_sxLdjEAfJ_oNog1P5kXm70NMHNXmzSMo_U,29008
|
64
66
|
sglang/srt/configs/step3_vl.py,sha256=_Otgnym57DVgB_kZ__8c1_Ys5gSalA_K0ZuVjcG51T0,4845
|
65
67
|
sglang/srt/configs/update_config.py,sha256=GEf-XhL8JPrbX9-Hz8V7S3M6YTg76DVdIhc_4YdMDtc,6291
|
@@ -85,12 +87,12 @@ sglang/srt/debug_utils/dump_comparator.py,sha256=3rWdv4BQXTDtB3z5ao9VPN5lK31ImKf
|
|
85
87
|
sglang/srt/debug_utils/dump_loader.py,sha256=RzWpl7RsDRw98DJMEvf6U9c9fPiobyeWI8opmRaRGGA,2632
|
86
88
|
sglang/srt/debug_utils/dumper.py,sha256=6frfI4WErneQE4RpXgAR5gZJQRdzcQjyO3McW56jgYo,3517
|
87
89
|
sglang/srt/debug_utils/text_comparator.py,sha256=NLJdjUikW--bWnGQWIeFJesyuvZ2Vni2S53fIED-m8s,7370
|
88
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
89
|
-
sglang/srt/disaggregation/decode_kvcache_offload_manager.py,sha256=
|
90
|
+
sglang/srt/disaggregation/decode.py,sha256=hfgpD-MYlJDQK5EmCgvRBdIUnm39SPBdPKQ5PEeEeQI,36260
|
91
|
+
sglang/srt/disaggregation/decode_kvcache_offload_manager.py,sha256=jD_O-uRaZ5cD8C9qtto6m5ZXyM86loJzkdLgwheMBao,7045
|
90
92
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=BeGxXbFLW_ZbuyOs0idWzlicCh6NA1pTOXgON5SAdaE,6947
|
91
93
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
92
94
|
sglang/srt/disaggregation/mini_lb.py,sha256=JY2uCeUM3Zk3FdGWmCQBY3LeiJ5FM1PlrqAW8wJTTHI,395
|
93
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
95
|
+
sglang/srt/disaggregation/prefill.py,sha256=yknkSqcMm9GbqjoDGD5QA1taMMrGsuNBmhgWYvAiByI,36203
|
94
96
|
sglang/srt/disaggregation/utils.py,sha256=oBMqYOMAnyK4T69fFaDIuM1AAGa2vOvoA-CBtGocOkk,12263
|
95
97
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
96
98
|
sglang/srt/disaggregation/ascend/conn.py,sha256=Z0xTJjSYXal7uGA5e7ci4oxOcWdC9qrV-gMd06ikp2w,4109
|
@@ -106,7 +108,7 @@ sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoO
|
|
106
108
|
sglang/srt/disaggregation/mooncake/conn.py,sha256=01TcfkekA3v7ApN11ATx_YsFi6B5U1xd3yPDxRx6F9Y,50697
|
107
109
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=O-XRmQ3QwD6RuiyRgw4ZohSrFkuPdppV_eDBMUXn0jk,5884
|
108
110
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
109
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
111
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=grkU7hz8w6R95UQ4M7i4dJ2Sces5fkvRNzrES_LkH2o,33379
|
110
112
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
111
113
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
112
114
|
sglang/srt/distributed/naive_distributed.py,sha256=5Kcfapzz61G3TtScTZrHoWa4bf6Vr27GlMcBAGMz7tQ,3260
|
@@ -128,22 +130,23 @@ sglang/srt/distributed/device_communicators/symm_mem.py,sha256=EFN6v2l3Hrxek_1kx
|
|
128
130
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
129
131
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
130
132
|
sglang/srt/entrypoints/context.py,sha256=aD-94xkD0komuGO5gtYUoJKCHdc4hAipMxQt04yVRGA,8030
|
131
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
132
|
-
sglang/srt/entrypoints/grpc_request_manager.py,sha256=
|
133
|
-
sglang/srt/entrypoints/grpc_server.py,sha256=
|
133
|
+
sglang/srt/entrypoints/engine.py,sha256=Nixu4vgnKTD--PbP1Hd6J0waphXSnKI-yKEzDOvnR2E,34947
|
134
|
+
sglang/srt/entrypoints/grpc_request_manager.py,sha256=5KzefIaYhlcYGk3A9tZlb5-TvTdnsa4AZF3pNIEdTAY,31805
|
135
|
+
sglang/srt/entrypoints/grpc_server.py,sha256=ES7qLcHxpoqLr587LxxZjdXChqEGPe8PZzHYvHGtXIM,36671
|
134
136
|
sglang/srt/entrypoints/harmony_utils.py,sha256=01T-A5GBUm2b306PcxNEg2rfx4cykBcqNYrzcXTWBlc,13590
|
135
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
137
|
+
sglang/srt/entrypoints/http_server.py,sha256=O96jlOHw8-Aj14GdnIQ4uT_eDt7KmCRZbHnwq_T5dho,53859
|
136
138
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
137
139
|
sglang/srt/entrypoints/tool.py,sha256=aAXEjBqkr5j6_IgRL8fZCKgoDPY2TikM20-LQXU9TaI,2709
|
138
140
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
139
|
-
sglang/srt/entrypoints/openai/protocol.py,sha256=
|
141
|
+
sglang/srt/entrypoints/openai/protocol.py,sha256=hdspAS9Ch-hS1hGPHTXGafTtk7JyKAzzM--JMOfeQsU,37807
|
140
142
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=b15N627nn3me2jHzXJBFkWPpX8OJdtD66v8aSsx0i0s,7746
|
141
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
143
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=roYXKtfBjB0HhQlsBpmwor8bO7B6xPHyMEhKaqOVD9I,47390
|
142
144
|
sglang/srt/entrypoints/openai/serving_completions.py,sha256=SBoaa9KIIL7NQCWwB1B2A9roTrQW1P9C4fkhuHymo00,18233
|
143
145
|
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=H7Nv1vSUuyOUXBeaNvYB4XMFxmcJc8or7MUKyuAw_XA,6435
|
144
146
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=G79XdomjzLhH1YCbGR4alSxWO9NNmi7U-YSPsH61cjk,3379
|
145
147
|
sglang/srt/entrypoints/openai/serving_responses.py,sha256=ro1VwdazJNqm5RRVbMKI7NliPsVMFcrNEsRD23QiADc,54989
|
146
148
|
sglang/srt/entrypoints/openai/serving_score.py,sha256=LuwXzWRAMm-xMK8ZjP3JaJ84Gxjr0Oi-e3keCsIgK38,1992
|
149
|
+
sglang/srt/entrypoints/openai/serving_tokenize.py,sha256=kgLBC8a_j16T2Gm5nv4DaUjjt9voerrbe-LrB5hJz-0,5525
|
147
150
|
sglang/srt/entrypoints/openai/tool_server.py,sha256=rRNGELPV5RHONp55MYkO4_b0NPsPffJnWg-gMYwDSTc,5659
|
148
151
|
sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_WKaSg9X45YdzERDxbtCY,2746
|
149
152
|
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
@@ -163,7 +166,7 @@ sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhF
|
|
163
166
|
sglang/srt/function_call/deepseekv31_detector.py,sha256=hpRjjv219mH0v1PQpMvj_gezrP7PwvLiNbBKOTCSC3U,9731
|
164
167
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=DhO3tUX1nvFlfRkHJ1Vm_7OMXFFTvWBA9u9SZKFAwuQ,9710
|
165
168
|
sglang/srt/function_call/ebnf_composer.py,sha256=OpjfvYowLlMLnxz5fwS7zv5-d43_ZwO9ucGAMsILvm4,15321
|
166
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
169
|
+
sglang/srt/function_call/function_call_parser.py,sha256=t7TUoOYbnfcLVjoP7-KtGTSpR6Tfc-js8paQ9lrqGPg,8656
|
167
170
|
sglang/srt/function_call/glm4_moe_detector.py,sha256=fUqozcc_V2g4Vd0l3BjhZZ0MRKmLinx98-Gm8aOlVgI,6975
|
168
171
|
sglang/srt/function_call/gpt_oss_detector.py,sha256=f0fjnxNKLb_TrxvNWbmCOB3_KN07NtZacazFpyIcqC8,9262
|
169
172
|
sglang/srt/function_call/json_array_parser.py,sha256=i985g7MUHj1M8gJ0it3Lw663Bx1uh0biN_It13hnMxU,2227
|
@@ -177,9 +180,9 @@ sglang/srt/function_call/step3_detector.py,sha256=SAibrispu0peDQzqOG2-V93KGHtV6U
|
|
177
180
|
sglang/srt/function_call/utils.py,sha256=HeRwtWRrkwipIKM_EBfCgyNxy2It_7kAfPUcBhMERjU,4548
|
178
181
|
sglang/srt/grpc/__init__.py,sha256=dPeDsMRMW8WyHD6jolIpIlvlJsYLAhwewHhCTdu1MAE,21
|
179
182
|
sglang/srt/grpc/compile_proto.py,sha256=kiaVgK1eEcSMVd5mCed-5cs_78JIawjJ1jQ2U6mdYkg,6997
|
180
|
-
sglang/srt/grpc/sglang_scheduler_pb2.py,sha256=
|
181
|
-
sglang/srt/grpc/sglang_scheduler_pb2.pyi,sha256=
|
182
|
-
sglang/srt/grpc/sglang_scheduler_pb2_grpc.py,sha256=
|
183
|
+
sglang/srt/grpc/sglang_scheduler_pb2.py,sha256=DL1Bmc897o_BwxBbVigLsHGMAW_pqmHfcvVzqMx3LXY,16094
|
184
|
+
sglang/srt/grpc/sglang_scheduler_pb2.pyi,sha256=_-p1dQFgZTp1aFZw9rGYKqc4a9Kd8pZRFZamkDQN3q4,26421
|
185
|
+
sglang/srt/grpc/sglang_scheduler_pb2_grpc.py,sha256=fEC2O4asGBb0V5xHRqZZrpJaTrNBpTM8tS0CiO7xy-c,12633
|
183
186
|
sglang/srt/layers/activation.py,sha256=iWEi9wIdAf0xov0KU27JUB5FIl6dqCGQjbIm_9dVSfQ,13368
|
184
187
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
185
188
|
sglang/srt/layers/communicator.py,sha256=KzmCXRknuxlRnwdA3G38wRlVHYD_kf76mOZWhaIU5lo,24366
|
@@ -188,8 +191,9 @@ sglang/srt/layers/elementwise.py,sha256=tGbN7bbK2s-j3DoJeJfkfyPNmKdVAutAd0J3TbxU
|
|
188
191
|
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=hnVVS_VsWukTYhREubWs2KcJ1GjVMEI9ECqxqOMXZv8,6729
|
189
192
|
sglang/srt/layers/layernorm.py,sha256=WKAv4N6LFDLu9x62XBqGT9xEcrj2W53GtP8ji4zTbTM,11335
|
190
193
|
sglang/srt/layers/linear.py,sha256=z15L32URxbPUb34_urGDwSWIZNfh1jmyKUF1A9lzI9I,55761
|
191
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
194
|
+
sglang/srt/layers/logits_processor.py,sha256=7NFCjFzOgjjFbgo1QlgTlPI2AyNvqyIut_pYofStTaM,34383
|
192
195
|
sglang/srt/layers/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
196
|
+
sglang/srt/layers/modelopt_utils.py,sha256=Abhiwmu1VOoSePJWytgFxRw_6qTtN2rqT61DPDboCIw,335
|
193
197
|
sglang/srt/layers/multimodal.py,sha256=vNswe0J0maeBiN8ehlmxfs-YYlrmMllYl6Nc_Y57Neg,5114
|
194
198
|
sglang/srt/layers/parameter.py,sha256=6ce1lx2urWJKz87g2qg_oce_S5BV0IcguSiOGGHbcC8,18378
|
195
199
|
sglang/srt/layers/pooler.py,sha256=uZ6WX1FLMEafZwusyZdm6KuVlIwSjbKrdwk2qzgqNGk,3812
|
@@ -202,24 +206,24 @@ sglang/srt/layers/utils.py,sha256=58yO8aKsAvS0jJ3nhOWVR_WAc5oTFiMeAERWNkXGR-I,19
|
|
202
206
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=x0421kNUgnAb5LnkJR6O67vGZ0ikSD-ThluV3QGsZ_8,22673
|
203
207
|
sglang/srt/layers/attention/aiter_backend.py,sha256=oovonzjvnijaegNmkyTlWlEhCuhXAMNd85EykvKvvow,43923
|
204
208
|
sglang/srt/layers/attention/ascend_backend.py,sha256=JwbuW4a-urczuVHEP7oRGOehJOcfUO71LCG3BiQq-zA,27206
|
205
|
-
sglang/srt/layers/attention/attention_registry.py,sha256=
|
209
|
+
sglang/srt/layers/attention/attention_registry.py,sha256=E3PpUTKQTbpeKn-RILkjVczpGIqoqAsn22EJe5-H9ds,7134
|
206
210
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=AGCPd_VqvvZ0tLExCEs_9RenwhP7nB47nNcbR9VuSJw,3831
|
207
211
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=cb2dMTnDMmMVBG_lqFRciVDiF3PeEAcXYaKDFWszeTw,9849
|
208
212
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
209
213
|
sglang/srt/layers/attention/dual_chunk_flashattention_backend.py,sha256=20vmnq68-Cq62UWIzQU_uwJzq4B8KdJeZUPVoWPiyDs,68620
|
210
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
211
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
212
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
214
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=aNZnEvcFh08cTLk2udyK8zxutVqgICfymvEH4PVASbo,105090
|
215
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=U6cWSQ-TOWNroUhRRgK9Ob0iFK0Oga3Df3N-QMVV9eQ,63032
|
216
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=KmghfUdEmQHa3OW7d12Kf_DpPJUOrd48Wpn0TeG5Sgs,39395
|
213
217
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=QqQgWIcF90wVqcvsxJR7lHtCtAqkNd9Rdl-tLq7cHHk,20852
|
214
218
|
sglang/srt/layers/attention/hybrid_attn_backend.py,sha256=Mp1M83ODwHENVvefP2JEjv47ifDt5SA1hoyrJo4OJyU,5128
|
215
|
-
sglang/srt/layers/attention/hybrid_linear_attn_backend.py,sha256=
|
219
|
+
sglang/srt/layers/attention/hybrid_linear_attn_backend.py,sha256=rmptVr26hFCMKyO-jxidU2TgKBeZsMkkzqy12dyeqMM,26226
|
216
220
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=IU_E7HkPrBLfNG2ArhI1ozHZ_pROujUzdI6g2JuToL0,4154
|
217
221
|
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
218
222
|
sglang/srt/layers/attention/nsa_backend.py,sha256=yyN3TRmPyxDBaYKsV-c5upK_wEVV3MyjJocw20DCAVo,33190
|
219
223
|
sglang/srt/layers/attention/tbo_backend.py,sha256=MyEQ29I41LCOHXm4_g7J7sXSs5bNKWRlSa2EfqploD4,9185
|
220
224
|
sglang/srt/layers/attention/torch_flex_backend.py,sha256=MnnZLxi41R-d4P0cyklNyefSWOU-AdFEjr8pxJWNgdI,11711
|
221
225
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=NdWD2ArmS1lQN9mZIbS2rcHueBWColNxvhcLaQGAKGQ,9728
|
222
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
226
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=XEo6AM9vpKjA8WwEAz9G6Eafb9Taxo0WzsjfUJhupYs,43580
|
223
227
|
sglang/srt/layers/attention/trtllm_mha_backend.py,sha256=l6ZbRIZ9Q4rHbsULJ49_MKd32vWdr3IRF5Pi8Dnzv0M,27503
|
224
228
|
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=k3e-tD-YjiVs8kOzEXaakCI7g6MDLD99NXMtAscrBZY,29396
|
225
229
|
sglang/srt/layers/attention/utils.py,sha256=lx_jNw2VwlBe2VnDb1eXRRdN9WArw9rdWHTHqndUEFk,3174
|
@@ -235,23 +239,24 @@ sglang/srt/layers/attention/fla/fused_recurrent.py,sha256=yOSTwqcNSoPWwQD--tcCkV
|
|
235
239
|
sglang/srt/layers/attention/fla/fused_sigmoid_gating_recurrent.py,sha256=dlmOu-7DG6YoSNexT3YV8GudrFPn_RiYj-3hClWdy-c,6424
|
236
240
|
sglang/srt/layers/attention/fla/index.py,sha256=kQGcR1doARV324QuA-faNoyo6u8a_wb-DfiPe_bOdhY,1050
|
237
241
|
sglang/srt/layers/attention/fla/l2norm.py,sha256=XOs5nGdWROp3FW4fHSObC8sa_x697yDV0jt5UKuLllE,3783
|
238
|
-
sglang/srt/layers/attention/fla/layernorm_gated.py,sha256=
|
242
|
+
sglang/srt/layers/attention/fla/layernorm_gated.py,sha256=jKPy6QYM8aJSM33EAyf550-BybedueNQY_EbZRG-5R4,10121
|
239
243
|
sglang/srt/layers/attention/fla/op.py,sha256=Qc-zHwZY9-8Aw53AuuzNfpbPBwKgIvVMgtWcfJLl6A4,1695
|
240
244
|
sglang/srt/layers/attention/fla/solve_tril.py,sha256=-Z51hFsLER_Lzn8h21WRUajbVOA1wuu5TSEvaC2AvK8,14405
|
241
245
|
sglang/srt/layers/attention/fla/utils.py,sha256=yBYjW-blAsq_uZxZ961Dub3cUouIvl4DCKV9UqkQSJw,10474
|
242
246
|
sglang/srt/layers/attention/fla/wy_fast.py,sha256=zf6_76vq7yYtn9Ir1Le4RVOKLaPNF_4bNST3ePuH0cU,4407
|
243
|
-
sglang/srt/layers/attention/mamba/causal_conv1d.py,sha256=
|
244
|
-
sglang/srt/layers/attention/mamba/causal_conv1d_triton.py,sha256=
|
245
|
-
sglang/srt/layers/attention/mamba/mamba.py,sha256=
|
246
|
-
sglang/srt/layers/attention/mamba/
|
247
|
+
sglang/srt/layers/attention/mamba/causal_conv1d.py,sha256=0Im_XzEA965rT5r09-bm1We1BaPgq2g_yo5nbA7KwvI,4503
|
248
|
+
sglang/srt/layers/attention/mamba/causal_conv1d_triton.py,sha256=BZ04knBsI9p75P0wBYjr5dfExaaeMBVhFLj12xt5auk,37679
|
249
|
+
sglang/srt/layers/attention/mamba/mamba.py,sha256=qGGEzMVZDDG0dEdUrLxVfWhRa1UI5OLis7dVBMqUpl0,22517
|
250
|
+
sglang/srt/layers/attention/mamba/mamba2_metadata.py,sha256=6hkbWuV0do1lFXucgGusqR5ha784g5CB7P7hZaigRNM,8551
|
251
|
+
sglang/srt/layers/attention/mamba/mixer2_rms_norm_gated.py,sha256=C60rddCKuf3eD6KVt5vB60LlGD2dYiU9WZGTlEPaoDM,4689
|
247
252
|
sglang/srt/layers/attention/mamba/ops/__init__.py,sha256=r-IpDGRIwTqGJzZoWNGyHqsqqv8oF19pNHEb7_TZR9M,98
|
248
253
|
sglang/srt/layers/attention/mamba/ops/layernorm_gated.py,sha256=hmuL7vQ77aWFENCDsJDB7Nki5DDdMTEiQywbaU4FC04,5229
|
249
254
|
sglang/srt/layers/attention/mamba/ops/mamba_ssm.py,sha256=aCFsiBdBDYt3D5HT0lxt6Rru9-gPYZspBM_WpTGgHh4,13680
|
250
|
-
sglang/srt/layers/attention/mamba/ops/ssd_bmm.py,sha256=
|
251
|
-
sglang/srt/layers/attention/mamba/ops/ssd_chunk_scan.py,sha256=
|
252
|
-
sglang/srt/layers/attention/mamba/ops/ssd_chunk_state.py,sha256=
|
255
|
+
sglang/srt/layers/attention/mamba/ops/ssd_bmm.py,sha256=IGOJ67TLx2WQQwDFm9jw2OU8vTZc0daVUnQF6kcu2x4,6798
|
256
|
+
sglang/srt/layers/attention/mamba/ops/ssd_chunk_scan.py,sha256=n70BQM8Dpg7_shX87ay3QvBEUO4fEcmg1OopU88KPiE,18405
|
257
|
+
sglang/srt/layers/attention/mamba/ops/ssd_chunk_state.py,sha256=Qdzx_4DIwl1-g_c24lRWKfmLTL29rxn2aRELWfuUct0,20784
|
253
258
|
sglang/srt/layers/attention/mamba/ops/ssd_combined.py,sha256=ivE3zqD31W01W7_RgpRG8Tfh11Co4mjbz2H6fWzGBP8,8909
|
254
|
-
sglang/srt/layers/attention/mamba/ops/ssd_state_passing.py,sha256=
|
259
|
+
sglang/srt/layers/attention/mamba/ops/ssd_state_passing.py,sha256=pNjxxLYw2BsTwy5-m7RhgqTZ9H8uyQFX2GQVucWU4wE,10032
|
255
260
|
sglang/srt/layers/attention/npu_ops/mla_preprocess.py,sha256=n6iR86qvKTYY_mC1EMxMiyHQaXZ8pF9o2iNCV68BA0E,14540
|
256
261
|
sglang/srt/layers/attention/nsa/dequant_k_cache.py,sha256=ie1qLy7AAipFYS0EJFrunN8Mq97D9v-noWaJBYMiv0I,4973
|
257
262
|
sglang/srt/layers/attention/nsa/index_buf_accessor.py,sha256=jPYRgFfTdH_g83OUs9q3ncj2Y036ikBvflMjYEjrHGw,11481
|
@@ -272,21 +277,21 @@ sglang/srt/layers/attention/wave_ops/prefill_attention.py,sha256=viTUit0rxjVV5Ua
|
|
272
277
|
sglang/srt/layers/moe/__init__.py,sha256=P8OC-pUE5yeEr80QUDqSPwF9a9BAYPuaK7GNlQovsJw,863
|
273
278
|
sglang/srt/layers/moe/cutlass_moe.py,sha256=JKJED-4709ndP5AwhQ7Vi04GJjw5d9Xl_mWOsZPZ3U4,14298
|
274
279
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
275
|
-
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=
|
280
|
+
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=slqtSpnCbtdfXnVvxVeBb3ObdSS2KmcWvEPRKfF7_mg,7005
|
276
281
|
sglang/srt/layers/moe/flashinfer_cutedsl_moe.py,sha256=4TS3YLrmxn5dEHYUKeY7aohBXYeAsU8UCx846NXFTw8,6197
|
277
282
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=XzJPM9Z6YQ4ejrMrBFt3l1i7guBcdQTXo9-gT5H8AIA,3479
|
278
283
|
sglang/srt/layers/moe/rocm_moe_utils.py,sha256=07Z99bTV3B-b2Cbm-odhGpx2twxtnVpYvaDMBE1K3LM,4555
|
279
284
|
sglang/srt/layers/moe/router.py,sha256=eUNu_Uz5VB2FOZzZyYuZo5pokCVBS17_fcjHQbmvDSE,12181
|
280
285
|
sglang/srt/layers/moe/topk.py,sha256=HcvKwbew1W4NJ-IGCp2aietW3o3KQPRuC7siRrjavt4,32240
|
281
|
-
sglang/srt/layers/moe/utils.py,sha256=
|
286
|
+
sglang/srt/layers/moe/utils.py,sha256=pz3diEN6KlwiDhKetswIleO32fZFCjqTLF9TvBXOsLk,6512
|
282
287
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
283
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
284
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
288
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=1Bg4JfwvNmtNuGEKezBxhjfy2hS24XlLnVhrwBEMhRA,32172
|
289
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=noKrvk75lm4SKM2rTm4A8bl9kuwzrK0upEWlJKH8IEQ,26378
|
285
290
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=tis0ZJmih7gKHCurbLtY_o-bY3K4MOzQLYLC3ftIOf0,977
|
286
291
|
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=mKH6zTTuh_Z8Ceg6d1VWjGBI3iPBn1YfGO6udxIRAtU,23306
|
287
292
|
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py,sha256=1iX5ox2KT5sgLHrN6l4svsgtn1-q_6514Q_F1v83-iY,7747
|
288
293
|
sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py,sha256=QOdl5uhZ8--aryXnKObdspKonGcF6Tc_U9o_lC_opo8,27760
|
289
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
294
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=Mcdned8e5hI21DI5nGJ0FKU4t2yAsI18Ah9xoMM-Z34,39485
|
290
295
|
sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py,sha256=U93mxPPU2RP7d3QRSvoG3OCtUQIK8YhQfHf1ZGeREmY,3284
|
291
296
|
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk0nPWQelgvi1rV9Z72FetRo6p7E3rsYs,10986
|
292
297
|
"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
|
@@ -496,18 +501,19 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=Ai06BZ7uxMnk
|
|
496
501
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H200.json",sha256=phmhkQNz8DcLHPqN5tjmJqOgbX0BhQx9cP82fp_jyIQ,3236
|
497
502
|
sglang/srt/layers/moe/moe_runner/__init__.py,sha256=Dc4PH6HfzQDjJWL7iuZ-0qh8oRu7OtnH6IEl675pYiU,172
|
498
503
|
sglang/srt/layers/moe/moe_runner/base.py,sha256=GMdFI74BGO5HDjtel5QWI7W4CFix0BHkw_HrjVswhcw,8905
|
499
|
-
sglang/srt/layers/moe/moe_runner/
|
504
|
+
sglang/srt/layers/moe/moe_runner/deep_gemm.py,sha256=TFGU144cGvxeQSCyzM1A9p8U7bAUbEItF6VcVrxXugs,9355
|
505
|
+
sglang/srt/layers/moe/moe_runner/runner.py,sha256=MCrPZQuuTxD4NGdnRaIkLc-xy8yOnXZW3ThJ2L-ymu4,2845
|
500
506
|
sglang/srt/layers/moe/moe_runner/triton.py,sha256=YaPqGIX-5y25nxmjF54_ASYbr9Dw4RYze2cNV4cUg-Q,14433
|
501
507
|
sglang/srt/layers/moe/token_dispatcher/__init__.py,sha256=I5I1ySCHbyAW5cFQy9mpuqkSWqLclLmi2AspCkoP8ig,993
|
502
508
|
sglang/srt/layers/moe/token_dispatcher/base.py,sha256=BqqwuSETP47vTaHkUoQWTEeZcAkg0n_Dgka-PkFM4uc,4029
|
503
509
|
sglang/srt/layers/moe/token_dispatcher/deepep.py,sha256=LtsaJ3bR-HBQL9ZWjgbw-HaP-hcAqAgrmpO-829PL94,26293
|
504
510
|
sglang/srt/layers/moe/token_dispatcher/standard.py,sha256=_OSudEOHA5qHqR5TJqnylQxUYyk7ZnhRMGOf7sMCyt0,1526
|
505
|
-
sglang/srt/layers/quantization/__init__.py,sha256=
|
511
|
+
sglang/srt/layers/quantization/__init__.py,sha256=mp8oK4anKX0oZatQGFVBOo9NFZPWBx6QZnwSrJxF_d8,7817
|
506
512
|
sglang/srt/layers/quantization/awq.py,sha256=YuAkweqSvQQGTGQvg4VpNXevSaJvT8CROpiNzmY_3tQ,26980
|
507
513
|
sglang/srt/layers/quantization/awq_triton.py,sha256=4XwJbRNlFmlvjbMGtWF1Wvk26Kf96162vNEmuI5Kars,11737
|
508
514
|
sglang/srt/layers/quantization/base_config.py,sha256=ql3kwwnjVzZGh8BUcimMt8K6kFxQtVbR5WgZHXqkOqA,7245
|
509
515
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=pqSLo4gwazZ4ajdVzyouwh_Z5oVDbWq9wo8RnrMdY8o,13998
|
510
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
516
|
+
sglang/srt/layers/quantization/fp8.py,sha256=9ktqicslcmrTyDh54cO1ETwI0ygc-TTf3Scxpm385JA,53455
|
511
517
|
sglang/srt/layers/quantization/fp8_kernel.py,sha256=Mgigb6GmF66oCrgjS97IvDDSacNYb0u-VYAf4FChhqM,54849
|
512
518
|
sglang/srt/layers/quantization/fp8_utils.py,sha256=sxsjlqL7sWXwbgsxwfzFSkojyN3w8KQh1R99JEWdBl0,29191
|
513
519
|
sglang/srt/layers/quantization/fpgemm_fp8.py,sha256=dq7rJz-QB9LovmZZLBMK8YJEOr05wjVrtWLmSTkXjYw,7004
|
@@ -517,7 +523,7 @@ sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V
|
|
517
523
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
518
524
|
sglang/srt/layers/quantization/marlin_utils.py,sha256=aM3GU7b7rHNZE-tZjRSrtOaPWzSaMcLxck4he8MlEVI,26344
|
519
525
|
sglang/srt/layers/quantization/marlin_utils_fp8.py,sha256=iSjq-ikPOTU5plrWNTW4MletKLySIrNl5NhQmY6FyAo,12508
|
520
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
526
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=sATYHOUF-ii0SDYW88lyD9w-fYCwNPrfQgtdFWz0FTQ,59356
|
521
527
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=uoRhxJ8W_U_VFpbn03YEp0aCjbzqquWwonjuN7KBucw,19117
|
522
528
|
sglang/srt/layers/quantization/mxfp4.py,sha256=mb_DeJgrmEBS2CREZ09WsQVetxLozq3a4HhxqMq2amY,32993
|
523
529
|
sglang/srt/layers/quantization/mxfp4_tensor.py,sha256=bGeCXlIOhmFZFGWp_lITkIRDEgGUaLpawDvMy1cTOmA,5389
|
@@ -527,7 +533,7 @@ sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2
|
|
527
533
|
sglang/srt/layers/quantization/rocm_mxfp4_utils.py,sha256=Z4pYWl6ExOXq2qfTHorW16hVbJ-Rk4G8Wrxn_x8boHE,327
|
528
534
|
sglang/srt/layers/quantization/unquant.py,sha256=T8w0mPvtBM1JhGhle6NoDY9C4xfmPWHU_VEJZWSnUNY,16079
|
529
535
|
sglang/srt/layers/quantization/utils.py,sha256=d4eaS4-Z4q3GRgb4HDMr2EoWEdQCefrVdJufK6n_NQY,18509
|
530
|
-
sglang/srt/layers/quantization/w4afp8.py,sha256=
|
536
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=ks2mRJ8wQ4gyZ4rKpTGlIIpzBmQYuMYwo0Oj6R4mcXM,11590
|
531
537
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=ugLV4G4MDog-UuLqSnEasBqE3Hh6AqE5ZYI371ean90,10415
|
532
538
|
sglang/srt/layers/quantization/w8a8_int8.py,sha256=e5mrRf7AWfit-5dOn3Ul9nTLt6OJth6SgrVpEdnVdE8,37076
|
533
539
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
@@ -696,7 +702,7 @@ sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=PI9r3PH
|
|
696
702
|
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=a1b2P8-5PRNwW1ykXR7jJF94aUF3u3t3P9ad_R1k2PI,549
|
697
703
|
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=qiUuQn-InDLYVNDPFOxde2XB-qlE0fol0HPTkY5KN8g,3197
|
698
704
|
sglang/srt/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
699
|
-
sglang/srt/layers/quantization/quark/quark.py,sha256=
|
705
|
+
sglang/srt/layers/quantization/quark/quark.py,sha256=Xt8e8Ds7wKV2UyQ3rJq9cFUtSNmTSAnRLnC2OgTBLds,14687
|
700
706
|
sglang/srt/layers/quantization/quark/quark_moe.py,sha256=fWUAEvLoaiw_6oNC7TQW2pUuR2AeNI9AaGWNcUGDiSQ,7446
|
701
707
|
sglang/srt/layers/quantization/quark/utils.py,sha256=zZHRe9mjxGp16_OJ5Qy_UtnQgipl3ZRZUmruYvyEm_w,7445
|
702
708
|
sglang/srt/layers/quantization/quark/schemes/__init__.py,sha256=z1LHBPqkxAS6Wp70DWwESOSixWpIhIQwz1IHcWDdURQ,167
|
@@ -705,7 +711,7 @@ sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=sW57dU7H
|
|
705
711
|
sglang/srt/lora/layers.py,sha256=0XlVcBTT1InMsBoLfiOO7yOnlDrnpXD_08wKo84T4B4,11852
|
706
712
|
sglang/srt/lora/lora.py,sha256=FooB4hOW5uvZJrDrdqKwBExb-lX5Uw_Y1gjU9an8hzc,7669
|
707
713
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
708
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
714
|
+
sglang/srt/lora/lora_manager.py,sha256=GQCdny4gP2ebHUwbL9BJsxmDEkm9k-wd6EJu11GA4X0,18950
|
709
715
|
sglang/srt/lora/lora_registry.py,sha256=osbau-sQZ7BuCeGGpBMFy4w40GO5FGqRgRwDyxxgNmg,8167
|
710
716
|
sglang/srt/lora/mem_pool.py,sha256=qh-AA7HhJDKG_xF5-67WGhrV6ohMM4TQU5oY40LVulc,11485
|
711
717
|
sglang/srt/lora/utils.py,sha256=FeIb51m5EIcetP1Pgn8X17EfuE5tGipm5iurRg3RAZw,4424
|
@@ -729,37 +735,36 @@ sglang/srt/managers/io_struct.py,sha256=ZkxZpLbdEJTl92GtmaGfG0TDuuNpcC6YrvOXG6X7
|
|
729
735
|
sglang/srt/managers/mm_utils.py,sha256=b6n39SlbaFP2XdUvJYOfRQL1Gch8fP--VxpOGsRJ8tc,30917
|
730
736
|
sglang/srt/managers/multi_tokenizer_mixin.py,sha256=audn1iSNNVu3d0DamslN1e-KGvhRJ5d_pw68nucQOUU,21676
|
731
737
|
sglang/srt/managers/multimodal_processor.py,sha256=0mLkwu6CGRQtt3G2T1tS3PSsh6dpyivV-vAfIHfcMbQ,1764
|
732
|
-
sglang/srt/managers/overlap_utils.py,sha256=
|
733
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
734
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
735
|
-
sglang/srt/managers/scheduler.py,sha256=
|
738
|
+
sglang/srt/managers/overlap_utils.py,sha256=RynVMuypX-LRksNKkNPizjJZ2de85-MSeCQvft3KheY,1907
|
739
|
+
sglang/srt/managers/schedule_batch.py,sha256=9o3BzZZcrlgTfAAm89_g6tQVWHW-kSX6yc1-ikA1c7s,83146
|
740
|
+
sglang/srt/managers/schedule_policy.py,sha256=AyxQehOL-bSKhjrjykUJRq-rhiPJ9PwgrdyEVT2LkK8,28200
|
741
|
+
sglang/srt/managers/scheduler.py,sha256=XPFfWh_wLlUg5HvZJqd7BCURZaCMb0xHCaE4Zufg3-s,123358
|
736
742
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=SYZ91JNTHtqiBHUpkk_MboAiBFyl5U7ardLcYDAQ0OU,3689
|
737
|
-
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=
|
738
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256
|
743
|
+
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=Yxvtn_NYMNpGZx_WVr-Yu8rxTk16PZN6DKeJryLDaRs,13197
|
744
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=cjG1FDVIVFpfYHa96ykit-cgTPgpgpokz5fd6qHEYQ4,37439
|
739
745
|
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=62dv-rLS3acUncFNJd6S0P4jglJ5XY3CFIauB08xuJ4,11405
|
740
746
|
sglang/srt/managers/scheduler_recv_skipper.py,sha256=8rVQCBjn9f26Th4XbeUS3fEsvo1GI029Me28wMjcKRY,1103
|
741
747
|
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=K9gCx16TaoeRah4fSYpIw_sOzRKuNUw2AJa6__dt5Bk,6194
|
742
748
|
sglang/srt/managers/session_controller.py,sha256=FGADRGSkRmS76o_BQ2fivpgw0Q5Q-K0Ws3aezH41YSc,6041
|
743
749
|
sglang/srt/managers/template_manager.py,sha256=M4EshVv1OhKxUAGQPP4OntRkSkUVvG93457xsYfWnQk,11968
|
744
750
|
sglang/srt/managers/tokenizer_communicator_mixin.py,sha256=NshY8ibxS7EQQGSYEp1PAAli0UL0-J_XZFtpQr9BIS8,25048
|
745
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
746
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
747
|
-
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=9EoJ5ZbolfC8atvs6i6AFz9L9xHGj6OseaSLPezkVX8,11858
|
751
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=0kyF0uyadJHXfhEp576ooAX_SS22uCOsvnXfWSDOphQ,87692
|
752
|
+
sglang/srt/managers/tp_worker.py,sha256=A_-8WACVFkLb4tJbzNDCFTy___1w57g7xHl_VnKmihA,14788
|
748
753
|
sglang/srt/managers/utils.py,sha256=fE_RZl5q0sZl9EQZNLlX9VNOHINxh-TJLQoH26GW2Lo,4279
|
749
|
-
sglang/srt/mem_cache/allocator.py,sha256=
|
754
|
+
sglang/srt/mem_cache/allocator.py,sha256=TEAkK32vyYz7wow5bpZLlrzb3KHVXtw9h1KtGWg6kIo,18246
|
750
755
|
sglang/srt/mem_cache/allocator_ascend.py,sha256=aGsh_VMI0eYoAy3uKCYbpAMFxyXVTyu4JmdeGDWLLbw,4997
|
751
756
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=Bv84HD6e_yYdtmIQemK1m1OUViO0PnuAvOS9tDpQOJM,2795
|
752
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=
|
757
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=fkwFe1s87oL30lqbCfME9hdl1V6t7VmtXo8ziT1Cos0,3520
|
753
758
|
sglang/srt/mem_cache/evict_policy.py,sha256=yX8hFNQ_pdzuN4rMjYcByhQZLs-lRZdD0qDLkPe2ht0,627
|
754
759
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
755
760
|
sglang/srt/mem_cache/hicache_storage.py,sha256=5L57L_vzqYyNk5PRdKikxyaaMj1LkCkWD38Sd93IAe8,7958
|
756
761
|
sglang/srt/mem_cache/hiradix_cache.py,sha256=hSsz8k1foizh-wJUxDi9h0NQZNNmSQoH_YP4A4uLtms,35414
|
757
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
762
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=0MGswX-v-4gpqruNhr830hfvLJjsgcemb7zFEcmuuB0,60438
|
758
763
|
sglang/srt/mem_cache/memory_pool_host.py,sha256=T3lgq0dyjyvOGdx4nGSGZzm6fqkX9H0S0JzYaNGJJ7k,27659
|
759
764
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=zPnQLQhBZ6zsUpCQPSoNkrB9EEvpoDQS4mU7c3sRWjE,2171
|
760
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=
|
765
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=crJVY1-qP2zinkyxWNW4_Fh_1swG_q8YOmyDB_eXDc0,27209
|
761
766
|
sglang/srt/mem_cache/radix_cache_cpp.py,sha256=0twLAAR2EYWyfRiUVsb__s01ITraNEF9bXBPZFvul1U,9454
|
762
|
-
sglang/srt/mem_cache/swa_radix_cache.py,sha256=
|
767
|
+
sglang/srt/mem_cache/swa_radix_cache.py,sha256=Xz0C5lCFJ2ZQj1LCPmFwvgCRxHTnACcmjKx3lBafPRY,43033
|
763
768
|
sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py,sha256=tQZpz-H6HxNAQe9mYqt6aX8mfDZyu_fbJTcCNK-Ns1M,7179
|
764
769
|
sglang/srt/mem_cache/storage/__init__.py,sha256=HDzHFUVeOHlry7HlfL5tRd5HUA02N94p8uzA_Va8nlM,251
|
765
770
|
sglang/srt/mem_cache/storage/backend_factory.py,sha256=rN8OfnkROk1rFQpJeCkiXMucuI--Ez35h4physV6Ys4,7822
|
@@ -785,15 +790,15 @@ sglang/srt/metrics/func_timer.py,sha256=6-PYCeItVhsET6lc0BcFQfd0Tc3_wvJ8VHdp3mlW
|
|
785
790
|
sglang/srt/metrics/startup_func_log_and_timer.py,sha256=PRVg3Z2d5GBMFifZXR-VhzGcn9nmKTkqEU41VJKZmaI,4937
|
786
791
|
sglang/srt/metrics/utils.py,sha256=MGb3quRI39n4tgJS1e0UHI5TBX3D0MwsgiZFMW2EsSQ,1903
|
787
792
|
sglang/srt/model_executor/cpu_graph_runner.py,sha256=ypp5yIW2OhRX-Xmido5mWuzEFpd-ohlq2c2wEuSW71I,23415
|
788
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
789
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
790
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
793
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=WDLZLUmFn-kgsw75N9r5Kfy42mBmT2jj4oE-24x1jYE,34347
|
794
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=PNYrLXW7PYaHX27ja3EMbLIQbdXwDVPHGlYOT2fFJXE,41726
|
795
|
+
sglang/srt/model_executor/model_runner.py,sha256=fGasUIxFusPPx1mxKDFK_-Pe7uG9oczEjEHSsLPlFmk,89797
|
791
796
|
sglang/srt/model_executor/npu_graph_runner.py,sha256=HstTsIQF2QHCPMQH_AxKOu1Ulykw8q8Cpx7Q-u9Kq8I,3673
|
792
|
-
sglang/srt/model_loader/__init__.py,sha256=
|
793
|
-
sglang/srt/model_loader/loader.py,sha256=
|
797
|
+
sglang/srt/model_loader/__init__.py,sha256=Y4gehllriF0JNjly4rGhQPSkUrA9u9Lr-WbfZfBIs6k,1034
|
798
|
+
sglang/srt/model_loader/loader.py,sha256=DNDRGfdrvCboyhpt_qqw97PxkxL_gCwe8iLwBGmTq7c,71900
|
794
799
|
sglang/srt/model_loader/remote_instance_weight_loader_utils.py,sha256=_HnQD1Ab-Wv9oATOmwJe6aQaQD_Gs_yG9EsDCGJQWfs,2881
|
795
800
|
sglang/srt/model_loader/utils.py,sha256=KrOpyd_eefZC3zFnhnwxIKNTx9G-MmA6jIK3NQbTW0E,5002
|
796
|
-
sglang/srt/model_loader/weight_utils.py,sha256=
|
801
|
+
sglang/srt/model_loader/weight_utils.py,sha256=U2UVN4loPPEPGNErdgOhZIpeLlSOINqi5WQkPhcCFwM,44555
|
797
802
|
sglang/srt/models/apertus.py,sha256=UL2Rd1TDDXPb2N4rWyymI3JThG7KlrGIyBuDIFCitPE,26002
|
798
803
|
sglang/srt/models/arcee.py,sha256=Q6fujRESEnljzs8ls3XGsPtWxzfKfUa0QAvAekYzeBY,18981
|
799
804
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
@@ -815,12 +820,12 @@ sglang/srt/models/dots_vlm_vit.py,sha256=K6QzcHx38XAq9fmNRJ-iApScZ9FoV0lkn3JYkRs
|
|
815
820
|
sglang/srt/models/ernie4.py,sha256=3z14KFdYLR8J-zsm9oO1uBUeLlWrlkHoFKEYvKKJLKM,16079
|
816
821
|
sglang/srt/models/ernie4_eagle.py,sha256=E7f-ygCcY8pIoyTMKFyVC2uRcG59-_RaQTO4gd5_uWI,7223
|
817
822
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
818
|
-
sglang/srt/models/falcon_h1.py,sha256=
|
823
|
+
sglang/srt/models/falcon_h1.py,sha256=fkmsV0yPqlQ1j_UyJq7bSkTCjRx3T9WdQoUkSmsmasU,20954
|
819
824
|
sglang/srt/models/gemma.py,sha256=2atKwFN5wCsJCmBRmURX9vaCcFjxlFirL7xsnG5KPlI,14180
|
820
825
|
sglang/srt/models/gemma2.py,sha256=n2s3WLGVM3XDvOXwbi_h7tgeh5SDDv1VvifH680DmV0,16785
|
821
826
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
822
827
|
sglang/srt/models/gemma3_causal.py,sha256=o46BNbaiOeoOv2xVU6-lWZhrrjyGskdebve0_wviWfU,27338
|
823
|
-
sglang/srt/models/gemma3_mm.py,sha256=
|
828
|
+
sglang/srt/models/gemma3_mm.py,sha256=9JpkNj_u-8Af9RJJQbUNGOxWmvW3TbXUceoI6omb8jc,18030
|
824
829
|
sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnLcemC0,36405
|
825
830
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
826
831
|
sglang/srt/models/gemma3n_mm.py,sha256=94QLW3FfAcqhz0E-gti8rTizTL9ci6CjMTxYOv2vHac,20371
|
@@ -834,7 +839,7 @@ sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtY
|
|
834
839
|
sglang/srt/models/gpt_oss.py,sha256=7cjyN1v2cxP9vZNrMqeDorX20U9_I4YcSpz_b4x0zj8,43720
|
835
840
|
sglang/srt/models/granite.py,sha256=8q92shxVPAp_cJDohJATffSGd7Z0Oi-vF5jpY6DlK4s,19840
|
836
841
|
sglang/srt/models/granitemoe.py,sha256=j1rgZ62CbBioECjUblDCw_NneDQgY_QJODsI0fqXVO8,13779
|
837
|
-
sglang/srt/models/grok.py,sha256=
|
842
|
+
sglang/srt/models/grok.py,sha256=1dBXzNLW3e054Ifpb1SAjFTmbQOX4jnk2yQj8hV_Erg,40253
|
838
843
|
sglang/srt/models/hunyuan.py,sha256=RSZErx-Swt65kmfvSXJQJJ6KhjucuNY4UUVLWC8hWaA,31102
|
839
844
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
840
845
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
@@ -861,10 +866,11 @@ sglang/srt/models/minicpm3.py,sha256=Cflu4Tb2hxpjapRBZ5n4kX8a1nnFwffK-M8uHPRUra4
|
|
861
866
|
sglang/srt/models/minicpmo.py,sha256=st8I13Ere5RkRHHQQN1LgZh1ybUA3_buxaaE4XlV8ag,76123
|
862
867
|
sglang/srt/models/minicpmv.py,sha256=_CnCR2y3RaYxhONAKFpBIuPQBrqn9Od4o7QnJw8CLR4,35884
|
863
868
|
sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,3475
|
864
|
-
sglang/srt/models/mixtral.py,sha256=
|
869
|
+
sglang/srt/models/mixtral.py,sha256=xyeZGb80BHLjXupBRydEkR4ZhEDlFCiqR4-MRJ4asdw,17032
|
865
870
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
866
871
|
sglang/srt/models/mllama.py,sha256=OdX7brhyfGiMFPulxF77QOUi-Kcscg3Qo4ipyxzs9yA,39670
|
867
|
-
sglang/srt/models/mllama4.py,sha256=
|
872
|
+
sglang/srt/models/mllama4.py,sha256=5TXritQRS3jARDZfblTOBW8co5ECazh39iZD7j19rdg,36667
|
873
|
+
sglang/srt/models/nemotron_h.py,sha256=-xNHFMbUv45XwpIx9G6SGyPLrPLxB9BHGwPhzcpf4no,18096
|
868
874
|
sglang/srt/models/nemotron_nas.py,sha256=CoSAKqlbej4Xe30uY4w76iASBqeuJf8-imisDK00zEU,15964
|
869
875
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
870
876
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
@@ -904,7 +910,7 @@ sglang/srt/models/starcoder2.py,sha256=ts6LDIjQ2FVnyLk4s2K9COD01RRhewJDW-VlvoyAk
|
|
904
910
|
sglang/srt/models/step3_vl.py,sha256=4j7drPJT2h-QwFH7tK7zR96xnuGvrxNbestuZsflCxg,35666
|
905
911
|
sglang/srt/models/torch_native_llama.py,sha256=3xf6CzCiizJ8i94GIChpOLq9q64Xa519RtuEspPTZQk,18501
|
906
912
|
sglang/srt/models/transformers.py,sha256=laA2h39MPeiAWKv4DEg0ydre-1pyXWFSRga-nwy1HUk,10244
|
907
|
-
sglang/srt/models/utils.py,sha256=
|
913
|
+
sglang/srt/models/utils.py,sha256=ccg5dR8_Ooz1UTxl7_mcK5fIu82GRJkkVxaUcbN54uo,1833
|
908
914
|
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
909
915
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
910
916
|
sglang/srt/models/xverse_moe.py,sha256=nBtG_PAK8wcp1tW2l2Zby2oEOmtWAYzH5COH-_N5IAM,17072
|
@@ -937,7 +943,7 @@ sglang/srt/parser/harmony_parser.py,sha256=YweG4azWm5jmzYGaAHEXSaORpgWctPpSGQk_j
|
|
937
943
|
sglang/srt/parser/jinja_template_utils.py,sha256=_rtLpriMmodo-tBD8B9ifu3BsZFdaQQCDPRUqF26pIg,8006
|
938
944
|
sglang/srt/parser/reasoning_parser.py,sha256=3P5viZ4oCsz695rZULWnRKSYBJxouHjihdpZMBuY9yc,11159
|
939
945
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
940
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
946
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=G-SZFQYhr89IQwQ-HcZzsbC9AoybUYlIKWrobKV0YOE,15722
|
941
947
|
sglang/srt/sampling/sampling_params.py,sha256=yRkiwoZz0OrmmdMn2v63O5qkbns3Gv9MonxKYvyYcKc,6690
|
942
948
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
943
949
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
@@ -948,11 +954,11 @@ sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18ns
|
|
948
954
|
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=7QpNIGrZE8GEqe_B1vuLhpWPCAV9jY0Kr67Imbirycs,14201
|
949
955
|
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=nqnlTLzqfz-zYJvIFALXzfgbCJdrtslIhfCnxEkvQ5I,15897
|
950
956
|
sglang/srt/speculative/eagle_info.py,sha256=3JtRb60iCQzzi1JgreRhpGzC1aTs5Zbqv8XBDknnGHQ,29942
|
951
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
952
|
-
sglang/srt/speculative/
|
953
|
-
sglang/srt/speculative/ngram_worker.py,sha256=
|
957
|
+
sglang/srt/speculative/eagle_worker.py,sha256=k2gODMg4dqbdf63y7sGY50gsv81ARs4wo4JDyqrZHUQ,46904
|
958
|
+
sglang/srt/speculative/ngram_info.py,sha256=U3a-c2bhNeIqZV4sKbzh3Hz_lAiqN1YFuFrbiaf0nsU,16600
|
959
|
+
sglang/srt/speculative/ngram_worker.py,sha256=t05lgkBATs-mo45eloiqvMalsJKdHI7fZ2BTYEpXoxg,9720
|
954
960
|
sglang/srt/speculative/spec_info.py,sha256=R3FK3ghFBUDSIUuNUYf41kFwEzP2fDBIlGdc45sRc4Y,2608
|
955
|
-
sglang/srt/speculative/spec_utils.py,sha256=
|
961
|
+
sglang/srt/speculative/spec_utils.py,sha256=TKCrNBx4hnohRhedY6GJMfSCWiTiQZ2BqGWqsbG9VgY,20062
|
956
962
|
sglang/srt/speculative/standalone_worker.py,sha256=jcM_-7DMtRUMC9R0YeD6815kaWuftkFe8LIo7ThLVCc,4069
|
957
963
|
sglang/srt/speculative/cpp_ngram/ngram.cpp,sha256=j8D4xNaa8dv8CN9F5TG_yHxil-A79XiuMjyEE3ZUOSs,12962
|
958
964
|
sglang/srt/speculative/cpp_ngram/ngram.h,sha256=9OMOzO3KXEVbT5gEXjK-IRATI63in54LjeT_Xba5DSU,2492
|
@@ -963,8 +969,8 @@ sglang/srt/speculative/cpp_ngram/queue.h,sha256=m8OK4Nd6_yWnJkWxx-JRqUIOfzQwi3ap
|
|
963
969
|
sglang/srt/tokenizer/tiktoken_tokenizer.py,sha256=KJwr6Xlc7AdHegMTnAVKJlPpW59Z7AE27GTzFL78GwI,6222
|
964
970
|
sglang/srt/tracing/trace.py,sha256=5SKy8XA4KLaTcBO6ZJvJSP_IYK5--2RJN0Q6O6Vg10g,16110
|
965
971
|
sglang/srt/utils/__init__.py,sha256=M47TWjBX488QHsDCOTKHv-979SGOsnSu1wIWEqUaXnI,86
|
966
|
-
sglang/srt/utils/common.py,sha256=
|
967
|
-
sglang/srt/utils/hf_transformers_utils.py,sha256=
|
972
|
+
sglang/srt/utils/common.py,sha256=XUpm0LALcaqFIlNbme0tZLHLaQF2--ZqleZ3ro68dic,108958
|
973
|
+
sglang/srt/utils/hf_transformers_utils.py,sha256=eQnrc_hE_gSbe1KoEsa0hUUuKgqInsTpEBsbSpCged4,17333
|
968
974
|
sglang/srt/utils/patch_torch.py,sha256=yaVs6YNm63rFYBw-v59usYR3cmb_qX6F69L5dMfQCxg,3307
|
969
975
|
sglang/srt/utils/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
970
976
|
sglang/srt/utils/rpd_utils.py,sha256=F8FWL_mT05xKQYLrzCJ8Q_5zfZJ86dHxX6LEqpwC7rw,20743
|
@@ -976,12 +982,13 @@ sglang/test/doc_patch.py,sha256=P9PYjBIVlZHvP9M34qS-8m1scmDP27ciNJNvZOdrUKE,1614
|
|
976
982
|
sglang/test/few_shot_gsm8k.py,sha256=zalplyHOYCnIwAnSQg-xlZl-Q-wGuMfjLdl9EJnUN7U,4333
|
977
983
|
sglang/test/few_shot_gsm8k_engine.py,sha256=h88s3HzEStA1zjQkR-AgIEOQMwJMSnPHkX_wGBWXUYw,3907
|
978
984
|
sglang/test/get_logits_ut.py,sha256=XotfHBDbQDRuSrJLRErsrdIOA0WDflnrK9171E-2iWE,1822
|
979
|
-
sglang/test/run_eval.py,sha256=
|
985
|
+
sglang/test/run_eval.py,sha256=0DNXNsi6Ls6ZaOCy3FR_nktviD2-JUi5uHuQu5Uud00,7799
|
980
986
|
sglang/test/runners.py,sha256=Tn__rDchJRP7pAorTS6gAAtqdPIeexpoEvwOwohTsB8,34105
|
981
987
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
982
988
|
sglang/test/simple_eval_common.py,sha256=Fm9PYFk6bYCb8RyMWr-ODfoNMUIftahTTOCBh84qiM0,12888
|
983
989
|
sglang/test/simple_eval_gpqa.py,sha256=M6hpPs8l2Z4wUiyE7rCU1zyKoImXB4Z395Hgz43uvvQ,3293
|
984
990
|
sglang/test/simple_eval_humaneval.py,sha256=s8YuKIBkNUEOBP4XKsTMRdXGv5aRhl0oJyl-89lGk1w,5687
|
991
|
+
sglang/test/simple_eval_longbench_v2.py,sha256=P4xwsG_MJ7N0imkz3W4yNbFqRYFlX_W3GG8NdAQEx1o,11679
|
985
992
|
sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
|
986
993
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
987
994
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
@@ -989,27 +996,31 @@ sglang/test/simple_eval_mmmu_vlm.py,sha256=XpADoB825LUX-n4hDFOR3wkuowdLPB6sMHJEv
|
|
989
996
|
sglang/test/test_activation.py,sha256=bDBFl4Y30siXj7Ifl66fc2HytOrcZdHFiP2i9K8TIsY,3140
|
990
997
|
sglang/test/test_block_fp8.py,sha256=CNQE3CildtLO49ZegwhWBIN3QyvA0qI6p25xQeuUrWE,21824
|
991
998
|
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
992
|
-
sglang/test/test_block_fp8_ep.py,sha256=n4X6ZKwuUUbV5Ofjg64ptlaFGI1LbRXDfFiJW1ELHgY,10546
|
993
999
|
sglang/test/test_custom_ops.py,sha256=PenQ8zM1wj5xwiVEPVzD37pO-x90aOfFMpCRZenaKsY,5709
|
994
1000
|
sglang/test/test_cutlass_moe.py,sha256=WHCruIMzxzRzxQEeFEUtk0e0IefjiO0Kjfgnx42r0UI,10069
|
995
|
-
sglang/test/test_cutlass_w4a8_moe.py,sha256=
|
1001
|
+
sglang/test/test_cutlass_w4a8_moe.py,sha256=yCYOkGyCs_L1OFpOPrR4UczlITCF-0lTQ9JAXAQ_KAk,8933
|
996
1002
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
997
|
-
sglang/test/test_deterministic.py,sha256=
|
998
|
-
sglang/test/
|
1003
|
+
sglang/test/test_deterministic.py,sha256=cDIHsfwSf3g-r2f5E4fChoEiErogi_KDxJoDTlIZUdM,10593
|
1004
|
+
sglang/test/test_deterministic_utils.py,sha256=idNEYSe_Q1S7Cx7LmEjq5vHWzvr5o7Tc5ay0iLT7s2Q,2301
|
1005
|
+
sglang/test/test_disaggregation_utils.py,sha256=9_ywTOub4Qjco46ndi6r8QCPo2y4Fha0DgXwJL9xBcQ,4958
|
999
1006
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
1000
1007
|
sglang/test/test_fp4_moe.py,sha256=wvHbGMH1UBr_XVWYgX57Y2bLy9h2DPQH10_Hmf2q6iw,22436
|
1001
1008
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
1002
1009
|
sglang/test/test_marlin_moe.py,sha256=TOuYlVMx2Lv_IN3AMWsg5aGaxQF472E1B9ev_vvfU2Q,7971
|
1003
1010
|
sglang/test/test_marlin_utils.py,sha256=kC7IzN364mJT9xw0nKUP1V1OK1hkw6fQTBvD4nRaOz4,5151
|
1004
1011
|
sglang/test/test_programs.py,sha256=R-pzgNB-h_jjdJiW50hn83-nY7z5q5XcqPwugPnVF5Y,18916
|
1005
|
-
sglang/test/test_utils.py,sha256=
|
1012
|
+
sglang/test/test_utils.py,sha256=S-mDCDIE1TnSTIVFT6B_j40LYgR1PuubxRwapgWfiIs,55185
|
1006
1013
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
1007
1014
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
1008
1015
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
1009
1016
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
1010
1017
|
sglang/test/attention/test_trtllm_mla_backend.py,sha256=wp2_LSTwQ_vIdNPUCbEz7PA4doDU8sTWs6s6XVI0YnI,48874
|
1011
|
-
sglang
|
1012
|
-
sglang
|
1013
|
-
sglang
|
1014
|
-
sglang
|
1015
|
-
sglang-0.5.3.dist-info/
|
1018
|
+
sglang/test/longbench_v2/__init__.py,sha256=ZcOIPSyqbDI_tzB-qltXF67-4uMMPwCkkiWDVcDBDvQ,63
|
1019
|
+
sglang/test/longbench_v2/test_longbench_v2_eval.py,sha256=NI_Om4ODw5utUNsYjrj6nueebI4U5u4N2PKBtT5O27k,7352
|
1020
|
+
sglang/test/longbench_v2/validate_longbench_v2.py,sha256=mJa5Lh8XiSTXKrf5qopKuAfspSVbhoacnCkz6u4lYFQ,11635
|
1021
|
+
sglang/test/longbench_v2/validate_longbench_v2_standalone.py,sha256=gr0zif2c680hSyIHDVJ_NHYcrMquM3fpJ26mBtbm7zs,10909
|
1022
|
+
sglang-0.5.3.post1.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
1023
|
+
sglang-0.5.3.post1.dist-info/METADATA,sha256=loxII9inoAsHe-62sp7X-6p70tOP_cyEGejMCgd-rMw,24603
|
1024
|
+
sglang-0.5.3.post1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
1025
|
+
sglang-0.5.3.post1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
1026
|
+
sglang-0.5.3.post1.dist-info/RECORD,,
|