sglang 0.4.5__py3-none-any.whl → 0.4.5.post2__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sglang/__init__.py +2 -4
- sglang/bench_one_batch.py +23 -2
- sglang/bench_serving.py +6 -4
- sglang/lang/backend/anthropic.py +0 -4
- sglang/lang/backend/base_backend.py +1 -1
- sglang/lang/backend/openai.py +1 -1
- sglang/lang/backend/vertexai.py +0 -1
- sglang/lang/compiler.py +1 -7
- sglang/lang/tracer.py +3 -7
- sglang/srt/_custom_ops.py +0 -2
- sglang/srt/configs/model_config.py +37 -5
- sglang/srt/constrained/base_grammar_backend.py +26 -5
- sglang/srt/constrained/llguidance_backend.py +1 -0
- sglang/srt/constrained/outlines_backend.py +1 -0
- sglang/srt/constrained/outlines_jump_forward.py +14 -1
- sglang/srt/constrained/reasoner_grammar_backend.py +101 -0
- sglang/srt/constrained/triton_ops/bitmask_ops.py +141 -0
- sglang/srt/constrained/xgrammar_backend.py +27 -4
- sglang/srt/custom_op.py +0 -62
- sglang/srt/disaggregation/base/__init__.py +8 -0
- sglang/srt/disaggregation/base/conn.py +113 -0
- sglang/srt/disaggregation/decode.py +80 -11
- sglang/srt/disaggregation/mini_lb.py +58 -123
- sglang/srt/disaggregation/mooncake/__init__.py +6 -0
- sglang/srt/disaggregation/mooncake/conn.py +585 -0
- sglang/srt/disaggregation/mooncake/transfer_engine.py +77 -0
- sglang/srt/disaggregation/prefill.py +82 -22
- sglang/srt/disaggregation/utils.py +46 -0
- sglang/srt/entrypoints/EngineBase.py +53 -0
- sglang/srt/entrypoints/engine.py +36 -8
- sglang/srt/entrypoints/http_server.py +37 -8
- sglang/srt/entrypoints/http_server_engine.py +142 -0
- sglang/srt/entrypoints/verl_engine.py +42 -13
- sglang/srt/hf_transformers_utils.py +4 -0
- sglang/srt/layers/activation.py +6 -8
- sglang/srt/layers/attention/flashattention_backend.py +430 -257
- sglang/srt/layers/attention/flashinfer_backend.py +18 -9
- sglang/srt/layers/attention/torch_native_backend.py +6 -1
- sglang/srt/layers/attention/triton_backend.py +6 -0
- sglang/srt/layers/attention/triton_ops/extend_attention.py +13 -2
- sglang/srt/layers/attention/vision.py +1 -1
- sglang/srt/layers/dp_attention.py +2 -4
- sglang/srt/layers/elementwise.py +15 -2
- sglang/srt/layers/layernorm.py +1 -1
- sglang/srt/layers/linear.py +18 -3
- sglang/srt/layers/moe/ep_moe/layer.py +15 -29
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +145 -118
- sglang/srt/layers/moe/fused_moe_native.py +4 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/{E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json → E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json } +34 -34
- sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +46 -34
- sglang/srt/layers/moe/fused_moe_triton/layer.py +7 -0
- sglang/srt/layers/moe/router.py +7 -1
- sglang/srt/layers/moe/topk.py +63 -45
- sglang/srt/layers/parameter.py +0 -2
- sglang/srt/layers/quantization/__init__.py +13 -5
- sglang/srt/layers/quantization/blockwise_int8.py +2 -0
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py +12 -2
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +72 -77
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +4 -7
- sglang/srt/layers/quantization/fp8.py +131 -136
- sglang/srt/layers/quantization/fp8_kernel.py +328 -46
- sglang/srt/layers/quantization/fp8_utils.py +206 -253
- sglang/srt/layers/quantization/kv_cache.py +43 -52
- sglang/srt/layers/quantization/modelopt_quant.py +271 -4
- sglang/srt/layers/quantization/moe_wna16.py +2 -0
- sglang/srt/layers/quantization/utils.py +5 -11
- sglang/srt/layers/quantization/w8a8_fp8.py +156 -4
- sglang/srt/layers/quantization/w8a8_int8.py +8 -7
- sglang/srt/layers/radix_attention.py +28 -1
- sglang/srt/layers/rotary_embedding.py +15 -3
- sglang/srt/layers/sampler.py +5 -10
- sglang/srt/lora/backend/base_backend.py +18 -2
- sglang/srt/lora/backend/flashinfer_backend.py +1 -1
- sglang/srt/lora/backend/triton_backend.py +1 -1
- sglang/srt/lora/layers.py +1 -1
- sglang/srt/lora/lora.py +1 -1
- sglang/srt/lora/lora_manager.py +1 -1
- sglang/srt/managers/detokenizer_manager.py +0 -1
- sglang/srt/managers/io_struct.py +255 -97
- sglang/srt/managers/mm_utils.py +7 -5
- sglang/srt/managers/multimodal_processor.py +0 -2
- sglang/srt/managers/multimodal_processors/base_processor.py +117 -79
- sglang/srt/managers/multimodal_processors/janus_pro.py +3 -1
- sglang/srt/managers/multimodal_processors/mllama4.py +21 -36
- sglang/srt/managers/schedule_batch.py +64 -25
- sglang/srt/managers/scheduler.py +80 -82
- sglang/srt/managers/tokenizer_manager.py +18 -3
- sglang/srt/managers/tp_worker.py +1 -0
- sglang/srt/mem_cache/hiradix_cache.py +5 -1
- sglang/srt/mem_cache/memory_pool.py +21 -3
- sglang/srt/metrics/collector.py +9 -0
- sglang/srt/model_executor/cuda_graph_runner.py +9 -6
- sglang/srt/model_executor/forward_batch_info.py +234 -15
- sglang/srt/model_executor/model_runner.py +67 -35
- sglang/srt/model_loader/loader.py +31 -4
- sglang/srt/model_loader/weight_utils.py +4 -2
- sglang/srt/models/baichuan.py +2 -0
- sglang/srt/models/bert.py +398 -0
- sglang/srt/models/chatglm.py +1 -0
- sglang/srt/models/commandr.py +1 -0
- sglang/srt/models/dbrx.py +1 -0
- sglang/srt/models/deepseek.py +2 -1
- sglang/srt/models/deepseek_nextn.py +74 -70
- sglang/srt/models/deepseek_v2.py +494 -366
- sglang/srt/models/exaone.py +1 -0
- sglang/srt/models/gemma.py +1 -0
- sglang/srt/models/gemma2.py +1 -0
- sglang/srt/models/gemma3_causal.py +1 -0
- sglang/srt/models/gpt2.py +1 -0
- sglang/srt/models/gpt_bigcode.py +1 -0
- sglang/srt/models/granite.py +1 -0
- sglang/srt/models/grok.py +1 -0
- sglang/srt/models/internlm2.py +1 -0
- sglang/srt/models/llama.py +6 -5
- sglang/srt/models/llama4.py +101 -34
- sglang/srt/models/minicpm.py +1 -0
- sglang/srt/models/minicpm3.py +30 -200
- sglang/srt/models/mixtral.py +1 -0
- sglang/srt/models/mixtral_quant.py +1 -0
- sglang/srt/models/mllama.py +51 -8
- sglang/srt/models/mllama4.py +102 -29
- sglang/srt/models/olmo.py +1 -0
- sglang/srt/models/olmo2.py +1 -0
- sglang/srt/models/olmoe.py +1 -0
- sglang/srt/models/phi3_small.py +1 -0
- sglang/srt/models/qwen.py +1 -0
- sglang/srt/models/qwen2.py +5 -1
- sglang/srt/models/qwen2_5_vl.py +35 -70
- sglang/srt/models/qwen2_moe.py +15 -13
- sglang/srt/models/qwen2_vl.py +27 -25
- sglang/srt/models/qwen3.py +335 -0
- sglang/srt/models/qwen3_moe.py +423 -0
- sglang/srt/models/stablelm.py +1 -0
- sglang/srt/models/xverse.py +1 -0
- sglang/srt/models/xverse_moe.py +1 -0
- sglang/srt/openai_api/adapter.py +4 -1
- sglang/srt/patch_torch.py +11 -0
- sglang/srt/reasoning_parser.py +0 -1
- sglang/srt/sampling/sampling_batch_info.py +2 -3
- sglang/srt/server_args.py +55 -19
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +4 -4
- sglang/srt/speculative/eagle_utils.py +1 -11
- sglang/srt/speculative/eagle_worker.py +10 -9
- sglang/srt/utils.py +136 -10
- sglang/test/attention/test_flashattn_backend.py +259 -221
- sglang/test/attention/test_flashattn_mla_backend.py +285 -0
- sglang/test/attention/test_prefix_chunk_info.py +224 -0
- sglang/test/runners.py +5 -1
- sglang/test/test_block_fp8.py +224 -0
- sglang/test/test_custom_ops.py +1 -1
- sglang/test/test_utils.py +19 -8
- sglang/version.py +1 -1
- {sglang-0.4.5.dist-info → sglang-0.4.5.post2.dist-info}/METADATA +15 -5
- {sglang-0.4.5.dist-info → sglang-0.4.5.post2.dist-info}/RECORD +162 -147
- {sglang-0.4.5.dist-info → sglang-0.4.5.post2.dist-info}/WHEEL +1 -1
- sglang/lang/__init__.py +0 -0
- sglang/srt/disaggregation/conn.py +0 -81
- sglang/srt/lora/backend/__init__.py +0 -25
- sglang/srt/server.py +0 -18
- {sglang-0.4.5.dist-info → sglang-0.4.5.post2.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.5.dist-info → sglang-0.4.5.post2.dist-info}/top_level.txt +0 -0
@@ -1,44 +1,42 @@
|
|
1
|
-
sglang/__init__.py,sha256=
|
1
|
+
sglang/__init__.py,sha256=T-fZEjKP66Q1q3PB56oREs5U3zf6bL0fNcdIbW8jMhE,1652
|
2
2
|
sglang/api.py,sha256=vHiKBg8wwIdmrpnGclop5BzJ-1Q88emrlrfLwNCHg98,7010
|
3
3
|
sglang/bench_offline_throughput.py,sha256=OQb-AjL4UNymmir02ht43uzgaNsnO_I11nXSowKMqBI,13841
|
4
|
-
sglang/bench_one_batch.py,sha256=
|
4
|
+
sglang/bench_one_batch.py,sha256=9-LFvhT0rjNa-Z5L0g5OpKfD6J4sQviRQbos42Fwkmc,18932
|
5
5
|
sglang/bench_one_batch_server.py,sha256=8VYNhaQbWGP8TkNVuy_sPjD5FiuVZHamtGRWKwa-Z-Q,5962
|
6
|
-
sglang/bench_serving.py,sha256=
|
6
|
+
sglang/bench_serving.py,sha256=6SnFF7rku8iDDW2qbIyqgBYsdZ3q3li5YH3zhhQH0E4,57540
|
7
7
|
sglang/check_env.py,sha256=76itNLUw9KlqbiY1BI4u4YaMZaqyCNcrCLUIb6aHflM,8396
|
8
8
|
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
9
9
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
10
10
|
sglang/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
11
11
|
sglang/utils.py,sha256=GIcgiRHkZ-gyPxXOdn1qFF41jkg4-YdDxbPc4mzO-qk,16159
|
12
|
-
sglang/version.py,sha256=
|
13
|
-
sglang/lang/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
12
|
+
sglang/version.py,sha256=0X83evIykSgmyAZc6vNVTXV2UQlVTx0omf8sSLruwLk,28
|
14
13
|
sglang/lang/chat_template.py,sha256=MwNL5dNTe8g_l2ljZubnrazEgT2xEv-9O2D0Ezwxy4I,19658
|
15
14
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
16
|
-
sglang/lang/compiler.py,sha256=
|
15
|
+
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
17
16
|
sglang/lang/interpreter.py,sha256=OH1SFCm4rUCPO32MTo8j5V2Z13Jic7_r1GQOP1-aHaw,33234
|
18
17
|
sglang/lang/ir.py,sha256=gssBGxqQEVJmjR_PqG2yah48AsInGaO3CmnQ2boJThc,18769
|
19
|
-
sglang/lang/tracer.py,sha256=
|
18
|
+
sglang/lang/tracer.py,sha256=20B9w2W3d0D6xSUGZjKFszFuZAzsa3gvgdIgsXR8GtU,8176
|
20
19
|
sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
21
|
-
sglang/lang/backend/anthropic.py,sha256=
|
22
|
-
sglang/lang/backend/base_backend.py,sha256=
|
20
|
+
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
21
|
+
sglang/lang/backend/base_backend.py,sha256=tEutGCU5tni1xGlrIjAVvA9aflJBt2duKrIDzqabJWc,1975
|
23
22
|
sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
|
24
|
-
sglang/lang/backend/openai.py,sha256=
|
23
|
+
sglang/lang/backend/openai.py,sha256=n47Zq1GTFc5x1DpN6CYL9cF6dfrsM7iJndnf5jRKU14,16331
|
25
24
|
sglang/lang/backend/runtime_endpoint.py,sha256=CAVh3X9F80t_2tkJECF__7AdCQtqDg1AHDqIoKIPnvs,16755
|
26
|
-
sglang/lang/backend/vertexai.py,sha256=
|
27
|
-
sglang/srt/_custom_ops.py,sha256=
|
25
|
+
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
26
|
+
sglang/srt/_custom_ops.py,sha256=L7NuEaRD_Q6Q54n0NZnLXgWZURbnn8Tkg4NQedE6zgA,3616
|
28
27
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
29
28
|
sglang/srt/code_completion_parser.py,sha256=HhEUzdL-FVBsOot9tKDKA1l8Gdx8qsF1RRg-zHNpmLQ,5400
|
30
29
|
sglang/srt/conversation.py,sha256=WP72AZrZpiqc5RowucT2tW3jVCb1pb4veW_kpwYS4yY,28785
|
31
|
-
sglang/srt/custom_op.py,sha256=
|
30
|
+
sglang/srt/custom_op.py,sha256=J1PUcGaeJJjfAjp06BQsLpUkKyR1zsh9MvDiDlqqJsg,1129
|
32
31
|
sglang/srt/function_call_parser.py,sha256=buYENeNEP5bhsvD424yGCa9wOqSfVOZSRn6zLiSJp5I,23733
|
33
|
-
sglang/srt/hf_transformers_utils.py,sha256=
|
32
|
+
sglang/srt/hf_transformers_utils.py,sha256=N2f-gA8yUq-UP_TJT276gNbDNzmddWsmWnq3px6TIj8,9342
|
34
33
|
sglang/srt/mm_utils.py,sha256=1ScBunw_x4W8ebM_AcJ62-1T2mfT8NlMJqdAhkF1lb0,12367
|
35
34
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
36
|
-
sglang/srt/patch_torch.py,sha256=
|
37
|
-
sglang/srt/reasoning_parser.py,sha256=
|
38
|
-
sglang/srt/
|
39
|
-
sglang/srt/server_args.py,sha256=eb3zJIpljzHK_ajp_zJRgwRUM_00-S-7K15k2opaBK4,52467
|
35
|
+
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
36
|
+
sglang/srt/reasoning_parser.py,sha256=JnaEVW0KG1yJpn9uxmrjwErb9imzni05QDFjExryoqM,5584
|
37
|
+
sglang/srt/server_args.py,sha256=2K5KQJgJ8T2q1XAnMIuIRTN5p5soFStsHPPb3n5yhJk,54193
|
40
38
|
sglang/srt/torch_memory_saver_adapter.py,sha256=KG3wM9-xZsSdsmORofArnNR7hH55GEyFxaderCDcK9w,1853
|
41
|
-
sglang/srt/utils.py,sha256=
|
39
|
+
sglang/srt/utils.py,sha256=tbigwWXEsPOCD4rrOA4fzdZa4Qcf76GsagmgGW1DX4U,61565
|
42
40
|
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
43
41
|
sglang/srt/configs/__init__.py,sha256=vulncVn70WqIT6s0HaB8p_Q6FjOiaLwNZWpoJS9FIuQ,399
|
44
42
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -48,7 +46,7 @@ sglang/srt/configs/device_config.py,sha256=kfmpPOECqYxcRoY-ko0QZRhyiBWUGP2CMF51D
|
|
48
46
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
49
47
|
sglang/srt/configs/janus_pro.py,sha256=-QtJ4ZGZiAJb0AkOEcuCHzIKLw23nF8nRk3rdCcoUO0,19016
|
50
48
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
51
|
-
sglang/srt/configs/model_config.py,sha256=
|
49
|
+
sglang/srt/configs/model_config.py,sha256=oMXM1CardGkJThm0KgCxxgYnwXaJXFZzmUZIM_wugeU,22046
|
52
50
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
53
51
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
54
52
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -58,16 +56,22 @@ sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8
|
|
58
56
|
sglang/srt/connector/serde/__init__.py,sha256=MvBJ7FBJtnou-AD-EdsCdAIDCcA8kWvUNuRViILVJ-0,718
|
59
57
|
sglang/srt/connector/serde/safe_serde.py,sha256=Iv_mFsDvk-cXuw0WTykBZ2yGxW0jb82DwVqC7r3RmAU,750
|
60
58
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
61
|
-
sglang/srt/constrained/base_grammar_backend.py,sha256=
|
62
|
-
sglang/srt/constrained/llguidance_backend.py,sha256=
|
63
|
-
sglang/srt/constrained/outlines_backend.py,sha256=
|
64
|
-
sglang/srt/constrained/outlines_jump_forward.py,sha256=
|
65
|
-
sglang/srt/constrained/
|
66
|
-
sglang/srt/
|
67
|
-
sglang/srt/
|
68
|
-
sglang/srt/disaggregation/
|
69
|
-
sglang/srt/disaggregation/
|
70
|
-
sglang/srt/disaggregation/
|
59
|
+
sglang/srt/constrained/base_grammar_backend.py,sha256=ljTVWpBo3bolce-E_-mtHIY2XWez4qcyDPeaIeZyIhM,7454
|
60
|
+
sglang/srt/constrained/llguidance_backend.py,sha256=Kgd-PQVBQlKWsz506OpF_xSdNBhEbvFywzICTZg21iM,5729
|
61
|
+
sglang/srt/constrained/outlines_backend.py,sha256=XbmkZSJzJnnY7k11uj8Et3StfuOiFwRs3ID4IRYAA4Q,6839
|
62
|
+
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
63
|
+
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=XFxdZqvPofmtCeIMqR10NOyph06HwbdXfiVI8rIoV5s,3646
|
64
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=pWyJL15D7kdiavcAG7_hMZEfSXbNbcxGE68qtrsLFsU,7288
|
65
|
+
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
66
|
+
sglang/srt/disaggregation/decode.py,sha256=cB8Dc4eyH6BfRqwhgEyU3yvCw1XbFBaYlC9UaeMNERA,20948
|
67
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=7SJIcXPt-Fqpbs4dj93-4M30zFGY1AOEu6FCGlU1Uqg,7643
|
68
|
+
sglang/srt/disaggregation/prefill.py,sha256=gm1VCWXv_s8iy2bR8RCYV1qbtdq8wW1dkoZmCURd3Fs,11453
|
69
|
+
sglang/srt/disaggregation/utils.py,sha256=fXFdNQ9Mt-EnKqPfUpjG-f6bQhLKYxwKRppzWvWBBvY,2540
|
70
|
+
sglang/srt/disaggregation/base/__init__.py,sha256=KR8xXoRCDAy2U623mfP6ujXu42m1_F9EiudjrKu2I_A,130
|
71
|
+
sglang/srt/disaggregation/base/conn.py,sha256=gpf32bhYXWm_iaYB6WcrDaJ-UoL1ZzPI_xpi5pMhRQo,2443
|
72
|
+
sglang/srt/disaggregation/mooncake/__init__.py,sha256=1vacEHmWjf7zgbMPzsXKB08FqNKNCquJdUiDlO41BOk,122
|
73
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=byeMgsi3Ape6sTNbF9KIvuq_R6FZMaCwEk5VoLqzeUg,21117
|
74
|
+
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=MxDAB9ZetRF1pFS2LP3FVHPtQ1HjIt_SK3UMaYHZ94o,2604
|
71
75
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
72
76
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
73
77
|
sglang/srt/distributed/parallel_state.py,sha256=hoTgLYfHIKMb_tSwBTauuusJZ8oY9BsiubTTOF8UfIw,50713
|
@@ -80,47 +84,49 @@ sglang/srt/distributed/device_communicators/pynccl.py,sha256=G-Dut_QJHOUG0j7--Zq
|
|
80
84
|
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6EMz-oPS9J16WHo2Q_SRL1DtlJKK63Hfg,15349
|
81
85
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=bbruDIM1GgKIdB6gi71_I0mpB179I-qyvwKuSj1Kaic,20816
|
82
86
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
83
|
-
sglang/srt/entrypoints/
|
84
|
-
sglang/srt/entrypoints/
|
85
|
-
sglang/srt/entrypoints/
|
86
|
-
sglang/srt/
|
87
|
-
sglang/srt/
|
88
|
-
sglang/srt/layers/
|
89
|
-
sglang/srt/layers/
|
90
|
-
sglang/srt/layers/
|
87
|
+
sglang/srt/entrypoints/EngineBase.py,sha256=xoyvp6XAeDLY2_Q2Ng33H-fRhrXHv2ldJJKd-HuDhqE,1870
|
88
|
+
sglang/srt/entrypoints/engine.py,sha256=cO-Yq5i_hrn_yaAuhkHKkUUVXQmHXcTV4B-l76LjbwU,22137
|
89
|
+
sglang/srt/entrypoints/http_server.py,sha256=wYjyyiajP6SWa3auZHZIUJv30zioB0IwdFKXHlyT5zo,28431
|
90
|
+
sglang/srt/entrypoints/http_server_engine.py,sha256=ihA6y3GXRs28Y9U3SgdQcJQjnw_SVIby7QrVgiafX04,4846
|
91
|
+
sglang/srt/entrypoints/verl_engine.py,sha256=XLYdwTwhH0jTjw8xczgZXWfBXMRb_ur2bg4TN0dTwfI,6975
|
92
|
+
sglang/srt/layers/activation.py,sha256=pshilucJ66qSotOjvP7p3LmTBPVY6xBKkbwEpTLX_WY,5974
|
93
|
+
sglang/srt/layers/dp_attention.py,sha256=Tfw2BydGPAeLcDlyl0jzBLOtkiygJhgAcf63RGZhrEE,7535
|
94
|
+
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
95
|
+
sglang/srt/layers/layernorm.py,sha256=Z0N8S6vUX8F9SmPQi80pjaa6KGw5YJZYuVEqfgiZGV8,4546
|
96
|
+
sglang/srt/layers/linear.py,sha256=nC9MxJrFap1BEyqgFlBySH4IeQruIbcBp32cOhUl5Fw,52149
|
91
97
|
sglang/srt/layers/logits_processor.py,sha256=Vp8ibljVEezTr54xzeOcjiJR7JdYO8ItkO5nLIIMVu0,24206
|
92
|
-
sglang/srt/layers/parameter.py,sha256=
|
98
|
+
sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
|
93
99
|
sglang/srt/layers/pooler.py,sha256=rj2lygvleBnyLCBZ8I11HGMgpfIDsT0l3PIkshJwdu4,1606
|
94
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
95
|
-
sglang/srt/layers/rotary_embedding.py,sha256
|
96
|
-
sglang/srt/layers/sampler.py,sha256=
|
100
|
+
sglang/srt/layers/radix_attention.py,sha256=xcsEmKLZYu7K3RaYnMX67H86XLiKD8AGu0Ob-4oV8aU,3247
|
101
|
+
sglang/srt/layers/rotary_embedding.py,sha256=-LXRtNCoawKiKwrtyhO91bMRBxKf8Vh06fF4P0zSJ0Y,45775
|
102
|
+
sglang/srt/layers/sampler.py,sha256=pvtlV2L5RYiwsCr4A0tE1h_nou9grFbktFR8bcHMiLg,11404
|
97
103
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
98
104
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=QUxd4sELx6p3dHvEKmccPZ-phdd_9EjNdwjH3SJ9zxI,22238
|
99
105
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=X_GIbQuU9njtUEGdUP7E_KRhmGxj3UyPHNESlL3QaQ8,3264
|
100
106
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
101
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
102
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
107
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=9dv3cj7fRODFbc0v2pRLxmkFcSfLH5M-iVU_PpfaP3A,51364
|
108
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=YtMTgMhxxNrAbSoWTPJczgY4SR3WjnAPXPoJ2d5PUZY,46394
|
103
109
|
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=pnVhvVEK87iFW8gUb1G7X7c1tqro8R2DSEOFCnlV8Bo,30301
|
104
110
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=1RPFNtQOBw6BWxIjrzfJgA9Nx92udLbR-S5KXmqjxS8,10536
|
105
|
-
sglang/srt/layers/attention/torch_native_backend.py,sha256=
|
106
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
111
|
+
sglang/srt/layers/attention/torch_native_backend.py,sha256=K5hUqBgakk2COSQqsaxWs0yEVOHS-7BlOygZTOeI8kE,9444
|
112
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=oEEiUwHbm4rNw5ExbQ2c3n0TwAgkk77yuLFenj9bHOo,26902
|
107
113
|
sglang/srt/layers/attention/utils.py,sha256=J9mA-cbZT3uTlaKXo0HEAaeMei_TS2o4McTna9LVDCE,2750
|
108
|
-
sglang/srt/layers/attention/vision.py,sha256=
|
114
|
+
sglang/srt/layers/attention/vision.py,sha256=H7dQofAlZjC48Dr6bo4HBsZSLDhdrbHKChyGejeaEGo,11886
|
109
115
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=DPu_aCPgwPqKWZPEQmp_xA7MPbpV2ip-MEICCB470Ao,19120
|
110
116
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=BXUY8ARHBF2s9x9waiEwfZwcMgvuaJA0gxb4OeUZ_tY,31167
|
111
|
-
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=
|
117
|
+
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=6MOrfQDVJQMTUXv0T3vUSF7JA67hVXxWqIbfDGBdKYM,13965
|
112
118
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=Y66gZ37u0GKMPtI8n5MbO6uOxRuGEmKIG0IPbJTOqAM,6213
|
113
119
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
114
|
-
sglang/srt/layers/moe/fused_moe_native.py,sha256=
|
115
|
-
sglang/srt/layers/moe/router.py,sha256=
|
116
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
120
|
+
sglang/srt/layers/moe/fused_moe_native.py,sha256=IWoRLIEMhXH8KAB9jt5QSnhUtHn4SnbJ9dDO1LNTZ9o,4659
|
121
|
+
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
122
|
+
sglang/srt/layers/moe/topk.py,sha256=K-VU64nWBV07bu1Okn-uYbhz9gylq-KFNRYn2SFzu28,11129
|
117
123
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
118
124
|
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=ijqRzS-tb0LGnDU5hW-g0JH104ppADrWaUIDGxb9Feo,22919
|
119
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
120
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=
|
125
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=Qotud38bCHg1tUtNKNjHPl4yHAD8ofELjtb8zcoePss,36350
|
126
|
+
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=zQV7Qr-Zrcr3D3efVvZepRQM02bj5djHPsijPssavk8,20430
|
121
127
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
122
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
123
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
128
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=DRkGQ6vuk4d786_UWMBqYlw-9o75k-T_rdtLQLZldK4,55410
|
129
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=XofcceHnkmqhVczEIVqGSbsxps5LiYTGcaCk1Say9YM,24951
|
124
130
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
125
131
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
126
132
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ouRyZ5PEMPP2njPftCNhs-1g1y6wueWLmhI7G1SjV1k,4131
|
@@ -165,6 +171,7 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=43-UL9KEMoaiC0cRSzWFbg2PA
|
|
165
171
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=MW7KzNa7DcKm53u2Jh-mnb93A3ICefgQHkdKONJMfew,3255
|
166
172
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=0aSYzpv_cBAlpWCPrfGgNTCfae1KdKQnT56E8XFQl7A,3262
|
167
173
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json",sha256=JEOXj48phwoumZWBwNq9TpqxVwIrbnfot4QfAdzvLJI,3249
|
174
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=Lqom_VMIPduSZTZQdeL2Wl_x3r9q6RmI9bojJrYwQZ4,3255
|
168
175
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XmKFaMheq7NNrsvYCJteul0w809l_l460ZiDQC9ToGs,3262
|
169
176
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=5ro9O8Nf-7MB8NGCQ3QV5kB2k3iSWe0rdTz2A4W72CA,3732
|
170
177
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=5ro9O8Nf-7MB8NGCQ3QV5kB2k3iSWe0rdTz2A4W72CA,3732
|
@@ -175,8 +182,12 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=43-UL9KEMoaiC0cRSzWFbg2PA
|
|
175
182
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Y4WpmVGlGERHoeoQNGkQ-GC-MsEtMblqnAVuDbARJdw,3240
|
176
183
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json",sha256=RUkd9fW9WbajF_fFIzppsE1qyWGR5aRC4Cln-BPdu28,3254
|
177
184
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json",sha256=Sc9xK1wtRUqIzXppbutcq-Y2e9M0DZl2OGVzzB0aQuI,3265
|
178
|
-
"sglang/srt/layers/moe/fused_moe_triton/configs/E=
|
185
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=7YmtaXKnmX8DdYnUJ7WQFa7xjr2Yun9WIdQNoCf_K28,3255
|
186
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=3Zt4hbC3yJxWvP0T7K93YAPaUP8fQ1P1Wk0CGqtBga8,3259
|
179
187
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=0HPFNkhgQ_Yd0190i1bQSgth3q4zCfBgiRQJsITO-S8,3265
|
188
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=4B0SmzRQ2-PsBJcFe7neM1OKfWpsbiY4x6c6COQNMsQ,3254
|
189
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Piw4LN6d8QYrUahWsw3XUOtTMD1o3vHPwA94sGI56Gk,3242
|
190
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=3T8_rF2PEojhgTMyQ8DscXgJCWWdWfDPj4M434zWcA4,3243
|
180
191
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=TBscr1uWwpY0FrKQ5Y3EO_Qg6I97u4f_zjnWRvoeLvE,3260
|
181
192
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
|
182
193
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=uv-RwTNZT2n264dLo4eWxUpB3g7QqUyf2MFEGiRvoqQ,3251
|
@@ -250,29 +261,29 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=43-UL9KEMoaiC0cRSzWFbg2PA
|
|
250
261
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json",sha256=-RzUWSIAAsg6iA-8SPMa68hPpBVoUyMJs3dLP7edRu0,4323
|
251
262
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
252
263
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Uz5X80VcNBOaxshwVNUEittHk2zqB4HQCfTJ4TPG5aM,3274
|
253
|
-
sglang/srt/layers/quantization/__init__.py,sha256=
|
264
|
+
sglang/srt/layers/quantization/__init__.py,sha256=UOQcyCvKFkX0u_OPPex7X5X98iUR3lXgBnLbffu0n9g,12424
|
254
265
|
sglang/srt/layers/quantization/awq.py,sha256=VImnVCU_QBLFba6S88T0dJ-vLy6SMm3OLIMEdllDfVI,6663
|
255
266
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
256
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=
|
257
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
258
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
259
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
267
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=cu9-JiCZDfMfvB97Kv_-eEG87VX5bRFIllFkzpO_xIg,15122
|
268
|
+
sglang/srt/layers/quantization/fp8.py,sha256=Niu89OfZd4pIpkwZ1zd2Hrlffx0c5L5zkix6Lzi0Vys,40970
|
269
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=oYq-j5moiilrTndKTqF4mRxCvhB1nSYhPMC9VeqcR4w,32964
|
270
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=LwP0Z8jPlaWpGBKVd27xqSk0ATzuB9CeLNEXiPm8wXs,18583
|
260
271
|
sglang/srt/layers/quantization/gptq.py,sha256=e4rMz374-yQQqeAI77WPxfcAaRk38GeN2akEpvnC_Do,15141
|
261
272
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRn_imIw8kNgqdtb2lr7BettjgDgimbl1Rubnamjh8,11352
|
262
273
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
263
|
-
sglang/srt/layers/quantization/kv_cache.py,sha256
|
264
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
265
|
-
sglang/srt/layers/quantization/moe_wna16.py,sha256=
|
266
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
267
|
-
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=
|
268
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
274
|
+
sglang/srt/layers/quantization/kv_cache.py,sha256=-yaFTdB75T0BbvQeuIpH6rZoL3R8t6OIJVGB-xdtpCw,3492
|
275
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=Ff7qMv7CCWj0QY5gkDnwlQYLH1mbMtopbw8jXMLndXg,16616
|
276
|
+
sglang/srt/layers/quantization/moe_wna16.py,sha256=KtFr4lIslMA12yx4JjXXPOsa5OHjxXWA6scYCRQnFMQ,19483
|
277
|
+
sglang/srt/layers/quantization/utils.py,sha256=3fP11UCSWkFWW7oTfQ6_3I1ZXfHvRL4WIlTAXnT1Ues,5442
|
278
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=VhM36MKz02W3uPCi-9Ap0XpQPXBdL88ny3l_aEtUq2M,11766
|
279
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=_oOJMkMrRMU2WvzAsNsQubQaVYcJJx9kr7Pps5MW2dw,9002
|
269
280
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
270
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=
|
271
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
281
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=ssrSfCJ9ORpxsXNfCiKioxmrwY0alPTPd52YLEqiqlk,25634
|
282
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=no7gs-M8eEYvNd0XPoVudfb1mBweoSFfcHYoWytJeAY,26199
|
272
283
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
273
284
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=qcdRgoUNJWXqSimns-D987TW0OTk3uFuWNBX8Z6H8Fk,246
|
274
285
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
275
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=
|
286
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=NZurhURFpZKqfMfgyd7oHLTLThm_8AO7xBCY8F6i3Gk,5881
|
276
287
|
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=RdHQxWXwXqvio31192vsLaKjEr4f_DjpMPKlarY1IAk,3251
|
277
288
|
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=0vLaJgo5B9ti-XMFKJuvSoMGjsZQ-RhHSx4cC8Xji-U,3254
|
278
289
|
"sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=tkLjwLC_aVXhzuvo-2QHkojXZauPJsf3jNHFn1S7uRA,3244
|
@@ -425,16 +436,15 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
425
436
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
426
437
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json",sha256=FImA-TJ_tQDjqwoNWxS--sRDoKDXf9gamlME3tkxH58,3252
|
427
438
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=FFBjSWlpKXMxfAUUYUqXbOK_Hd7qBeBsfbcaa9uB4qY,3249
|
428
|
-
sglang/srt/lora/layers.py,sha256=
|
429
|
-
sglang/srt/lora/lora.py,sha256=
|
439
|
+
sglang/srt/lora/layers.py,sha256=cu1kqDCuH05ck8HVtwmVuMVBzcPJZeDY3mk486teB4E,11848
|
440
|
+
sglang/srt/lora/lora.py,sha256=uNvbjZ_Wr1SLI9-ElRJA_JKwkibSGroP5Bfpsr9MI-Y,7527
|
430
441
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
431
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
442
|
+
sglang/srt/lora/lora_manager.py,sha256=nyqkm7RLoQE6myfqcH9r0zwME4aEZ3pFkVjY36QTlvA,9200
|
432
443
|
sglang/srt/lora/mem_pool.py,sha256=xUFoHUDJgX9lt2YugD9HUY5tIMnJiazYMZ6LYqSGv-E,9633
|
433
444
|
sglang/srt/lora/utils.py,sha256=GjEBgsGhDhX4NqVqeaciznQ8RotKZmb2c-nw4YMLHxA,5251
|
434
|
-
sglang/srt/lora/backend/
|
435
|
-
sglang/srt/lora/backend/
|
436
|
-
sglang/srt/lora/backend/
|
437
|
-
sglang/srt/lora/backend/triton_backend.py,sha256=_QbqggFPHMPWgx3PI15yyyfxBCTxSpGA209x_frI12E,2517
|
445
|
+
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
446
|
+
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
447
|
+
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
438
448
|
sglang/srt/lora/triton_ops/__init__.py,sha256=JGOYPIn1XbGcyJTbt8A0qoc02PYONSGNNjGkC8yJpAM,283
|
439
449
|
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=CDGt7lpu9GjykgMtmwbZ3PEqjTlRYyh28AUlj1cRcmw,5279
|
440
450
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=HTfU3HxxxVyaG_aJrrVjPJTnqf62yvepcKJKYkG0XJQ,5944
|
@@ -443,70 +453,71 @@ sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=Q58UzWUb3QFqY_ZxWA3poN373N0Hwk
|
|
443
453
|
sglang/srt/managers/cache_controller.py,sha256=d4RGqbut1FlzJnpqr7WY_TYmRjYPS07OoOVbztjs5xI,18959
|
444
454
|
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
445
455
|
sglang/srt/managers/data_parallel_controller.py,sha256=Xkj2n9uDyq7a-AVDZlfzeuNkC4ibsSftb1_bed9hgQ4,10318
|
446
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
456
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=3S3aRvKSi75RQSxEEQkeyxKDNNunWiw9wlwsbT1VXSo,10099
|
447
457
|
sglang/srt/managers/expert_distribution.py,sha256=r3o5RGI0gnV7xb60AApqKYa0oiSB37oB7hQBX7P3xZM,3225
|
448
|
-
sglang/srt/managers/io_struct.py,sha256=
|
449
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
450
|
-
sglang/srt/managers/multimodal_processor.py,sha256=
|
451
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
458
|
+
sglang/srt/managers/io_struct.py,sha256=nNRAJXJpJvZFHFkOPHVa9TkzawlhZlfHpu4qlZsYPWw,30897
|
459
|
+
sglang/srt/managers/mm_utils.py,sha256=P-UbCdzasK0yR-xn6Lrk3ILct3uJrIBuXSDrtRZlB_A,15542
|
460
|
+
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
461
|
+
sglang/srt/managers/schedule_batch.py,sha256=pPKw8z7B_6tA9OZoMU2r_KPJzAx3aNjylZx2Hm1bEcw,62407
|
452
462
|
sglang/srt/managers/schedule_policy.py,sha256=E1qVq2G3jptKdX9nlqfayeRBUll9xB6bK8nBf3EW32E,19469
|
453
|
-
sglang/srt/managers/scheduler.py,sha256=
|
463
|
+
sglang/srt/managers/scheduler.py,sha256=SujQHQOzw-O1NDxgMF8JWI0nF-EdRDC2ynKOXp69cNo,79876
|
454
464
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=u2sj6MViFTov0lVZSysZ-wph2pEqRCtCjwA1UdttZ7I,26338
|
455
465
|
sglang/srt/managers/session_controller.py,sha256=o-ifit0n4_xHLNmyD0Ams8FxGRgxFybX-Vz1hwgr3UQ,5755
|
456
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
457
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
466
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=ukKGBjsVdI-FS3NF3sywxAHpWvK_eEOCDsfI0mPPPqw,46706
|
467
|
+
sglang/srt/managers/tp_worker.py,sha256=khF-hXOrtF_IesOyUSjEBjb7fAh3CakdiKR7Ebj2wp8,8894
|
458
468
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=3_ZJ8Rq7v2ZDaRNTRu5Dy8AbqiAlJQp3IAKnn_WAwd8,9127
|
459
469
|
sglang/srt/managers/utils.py,sha256=5i75uLlQOF_5CaT02CrWtwozMTtwTg2_nLP8Dtr-JZQ,1536
|
460
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=
|
470
|
+
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=M36x_Emm-IdpFiQpii3qyQZ79O7NZsyJgDT5gk08Plo,9923
|
461
471
|
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
462
472
|
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=j7j1D38azudJjYthVpdz7jxQ9Z7SjwQfskpOIshAdiY,3147
|
463
473
|
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=UlkyIoc8XOw69iFBYiBYLx--pdfnM4JfCFtwRrd3w-o,2267
|
464
|
-
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=
|
474
|
+
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=4bQZ7WByd53d1PcEgVeeXRyWnC78nO-8RsQbGWRDyYM,1852
|
465
475
|
sglang/srt/managers/multimodal_processors/llava.py,sha256=8mac3vUUpVd12o43k1TyMaLEySZB915ks8Q5epeZmbg,6209
|
466
476
|
sglang/srt/managers/multimodal_processors/minicpm.py,sha256=Mq-iH2j90VrGAbSaF3ayYWhTEm9RvWNI6ZhBb6G23dQ,5684
|
467
477
|
sglang/srt/managers/multimodal_processors/mlama.py,sha256=MLiGS606LzVtdoXvjWGANx-K_7nE9J_fMVmkXN7Gz8k,1661
|
468
|
-
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=
|
478
|
+
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=50Yox7TaGrrB7iPjN1dQ_UzuY41x7VLmMcRXBhTgUvE,5592
|
469
479
|
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=67EmFiAkvZncU-eqiiS0Q4dr3pWcfI-RofYiQnNWvu0,5722
|
470
480
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=NY62Zo0A0tLJ7ObRLOQqQcXCxoJUDZsK8f5U4dNQjKc,973
|
471
481
|
sglang/srt/mem_cache/chunk_cache.py,sha256=it5SfL1FwMbrdeOH-I-Eu_i-I9hFB1xL-z_brIUoCkk,1835
|
472
482
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
473
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
474
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
483
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=hCexDvC_BC5juQHAuzZRE4e9Stirq1ysfsB87uz5BcQ,16340
|
484
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=bMzNK-8avd-_rwKqTJHwMiQKXP4rrt6MmXbofFDWihQ,31753
|
475
485
|
sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
|
476
486
|
sglang/srt/mem_cache/radix_cache.py,sha256=Lm-pco6CJ4orb9IfDpbHm5MnyK8Ya0OF1x9p88dv548,14906
|
477
|
-
sglang/srt/metrics/collector.py,sha256=
|
487
|
+
sglang/srt/metrics/collector.py,sha256=zHg4twFQJvuK1mSme3-EYQa9PJryfp_u7a4RxQ5RcO0,8874
|
478
488
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
479
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
480
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
481
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
489
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=ZaN1yPju52iOVQwfCVju2Iw_ci4B87mI_xi21IZFZis,23325
|
490
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=_qSMTiLxvcPIIgqRfUqG4W--OoirVY7ulcFfZqQIqjo,28689
|
491
|
+
sglang/srt/model_executor/model_runner.py,sha256=mDPja0tc2NNa2UBf1GfpjTtowmCdDncSS06NkwzFnmU,46476
|
482
492
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
483
|
-
sglang/srt/model_loader/loader.py,sha256=
|
493
|
+
sglang/srt/model_loader/loader.py,sha256=YYmtvkQw0B1qgPw0_gN-K4yy7CEYbTSR__0Dl1Fnm6k,55342
|
484
494
|
sglang/srt/model_loader/utils.py,sha256=0NaMR67fESFopaklmsleiL27XH1QUrjZW246MUu1EJ0,1369
|
485
|
-
sglang/srt/model_loader/weight_utils.py,sha256=
|
486
|
-
sglang/srt/models/baichuan.py,sha256=
|
487
|
-
sglang/srt/models/
|
495
|
+
sglang/srt/model_loader/weight_utils.py,sha256=yKnau-wH9muczoCpDTCVIqXFqz-QJmEEySplX3bMJWk,32153
|
496
|
+
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
497
|
+
sglang/srt/models/bert.py,sha256=kHlErDgNX_mIhfWWCnAcH_ncvYg22Y61gI34gW8GuUY,12738
|
498
|
+
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
488
499
|
sglang/srt/models/clip.py,sha256=fCMtAcaKjruSIWfD4YGb4HXh6Tzp2pjpgDmp5JpwBPU,19794
|
489
|
-
sglang/srt/models/commandr.py,sha256=
|
490
|
-
sglang/srt/models/dbrx.py,sha256=
|
491
|
-
sglang/srt/models/deepseek.py,sha256=
|
500
|
+
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
501
|
+
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
502
|
+
sglang/srt/models/deepseek.py,sha256=m8CjJIJiQ9B_ACPy7dwMLfm4kVLXcuW27zDk_lcQ_Dc,16920
|
492
503
|
sglang/srt/models/deepseek_janus_pro.py,sha256=8wAzvcGdyo--3faMN4QtagT1eAZMhMFduvpCXqUS48Q,70456
|
493
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
494
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
504
|
+
sglang/srt/models/deepseek_nextn.py,sha256=mL2nnblFmeBD8cSf15BmJh_M-8dyCx07sqlicw4rab4,13454
|
505
|
+
sglang/srt/models/deepseek_v2.py,sha256=dAjHJ_2aRZSd0OQ0uCinDmRYpVs1tEWEeDfXy_NrdxQ,68369
|
495
506
|
sglang/srt/models/deepseek_vl2.py,sha256=RVvi_3qsfrkqMCCnjjTA8OwUc5ySutc7asAH-rUJLVo,12922
|
496
|
-
sglang/srt/models/exaone.py,sha256=
|
497
|
-
sglang/srt/models/gemma.py,sha256=
|
498
|
-
sglang/srt/models/gemma2.py,sha256=
|
507
|
+
sglang/srt/models/exaone.py,sha256=rX7J0xFt9TSt6tMIhnYMkb5KDnqTJIV4BtjPLFwQ8_8,13425
|
508
|
+
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
509
|
+
sglang/srt/models/gemma2.py,sha256=kqtwdo93GWKm2iBN29RoIRH2ggRm-K_80LM5btgfBLo,16395
|
499
510
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
500
|
-
sglang/srt/models/gemma3_causal.py,sha256=
|
511
|
+
sglang/srt/models/gemma3_causal.py,sha256=G_vNxBZBJOVigZg8B3XGtbSmak9LEtSFFr9uQMXBHQY,24973
|
501
512
|
sglang/srt/models/gemma3_mm.py,sha256=tWX2vIdRf5zePwKMLbb0d24DUWoTdjmdXnxIcULQJ2E,15221
|
502
|
-
sglang/srt/models/gpt2.py,sha256=
|
503
|
-
sglang/srt/models/gpt_bigcode.py,sha256=
|
504
|
-
sglang/srt/models/granite.py,sha256=
|
505
|
-
sglang/srt/models/grok.py,sha256=
|
506
|
-
sglang/srt/models/internlm2.py,sha256=
|
513
|
+
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
514
|
+
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
515
|
+
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
516
|
+
sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,28033
|
517
|
+
sglang/srt/models/internlm2.py,sha256=RDAT9drjdgVEFmCMq99RTn3weMQFhl1NHhkhyDX8f7M,13056
|
507
518
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
508
|
-
sglang/srt/models/llama.py,sha256=
|
509
|
-
sglang/srt/models/llama4.py,sha256=
|
519
|
+
sglang/srt/models/llama.py,sha256=Y4ROe8ohP84G4vin_Sr_vjG0XRoM5gGgnrojxOXn_uc,24942
|
520
|
+
sglang/srt/models/llama4.py,sha256=JIVS5Q1lnmEpAHDI487gKO_9xfTCehSpzInNQeCg8JU,17940
|
510
521
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
511
522
|
sglang/srt/models/llama_eagle.py,sha256=OB2lKsjn7BcfCZljklnhk83me8j0PuQmYLou7baNcq4,4866
|
512
523
|
sglang/srt/models/llama_eagle3.py,sha256=v3bftBVDIGjnzngQYnu19cy0J_3w7yruHqLP5nsAQDM,6642
|
@@ -514,38 +525,40 @@ sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OW
|
|
514
525
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
515
526
|
sglang/srt/models/llava.py,sha256=KMwNNrlMuMaKEOZMDRBKBQbe6uctpKTLc0zOceyGC34,27242
|
516
527
|
sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc,12829
|
517
|
-
sglang/srt/models/minicpm.py,sha256
|
518
|
-
sglang/srt/models/minicpm3.py,sha256=
|
528
|
+
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
529
|
+
sglang/srt/models/minicpm3.py,sha256=R5-9CHgyUnsnxYPwLP7LQA3AKQ10Igtphs5x7u98Oa4,19367
|
519
530
|
sglang/srt/models/minicpmo.py,sha256=kJnp8UwJTV7kXEpuVWA50ecRsuZyFedHlwkprix8tag,75619
|
520
531
|
sglang/srt/models/minicpmv.py,sha256=79zZn3co9r7SERatx49EuHRoLWRiy6qeaUFgjDWJo2I,40571
|
521
532
|
sglang/srt/models/mistral.py,sha256=EYifJUUzN2Z2-iL37eJiNZF_DB0H4pa0mKlgYRIxM70,838
|
522
|
-
sglang/srt/models/mixtral.py,sha256=
|
523
|
-
sglang/srt/models/mixtral_quant.py,sha256
|
524
|
-
sglang/srt/models/mllama.py,sha256=
|
525
|
-
sglang/srt/models/mllama4.py,sha256=
|
526
|
-
sglang/srt/models/olmo.py,sha256=
|
527
|
-
sglang/srt/models/olmo2.py,sha256=
|
528
|
-
sglang/srt/models/olmoe.py,sha256=
|
529
|
-
sglang/srt/models/phi3_small.py,sha256=
|
530
|
-
sglang/srt/models/qwen.py,sha256=
|
531
|
-
sglang/srt/models/qwen2.py,sha256=
|
532
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
533
|
+
sglang/srt/models/mixtral.py,sha256=zQHCL_ZMKmLR7jitpEw8n7Rv6xhxUJzSXklsw6auh2E,14965
|
534
|
+
sglang/srt/models/mixtral_quant.py,sha256=-kQw9r8KcLdO8SNN9RKXzrGq9Q2Al9l9cWHi1VrZSRM,15260
|
535
|
+
sglang/srt/models/mllama.py,sha256=jYV5ckyuJN5XU2VXjUgV1i-Yz5rZDQ-6OYsNZvUTJjo,39775
|
536
|
+
sglang/srt/models/mllama4.py,sha256=65_YDBaNSeJJuigz3sZKvsq25ZGO17MQIoya8ukJgRA,9086
|
537
|
+
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
538
|
+
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
539
|
+
sglang/srt/models/olmoe.py,sha256=TMzt-yB891bvA4X50xL0NjNnFYSx9imlA7N1EG8KNK0,15949
|
540
|
+
sglang/srt/models/phi3_small.py,sha256=UbqZvpwWolXUPd0zbKgbL93yVXUY1n4kXJLgIe_gjaM,15508
|
541
|
+
sglang/srt/models/qwen.py,sha256=xYkVmMZS2uMqWhfndc8EYm0olpKFnggfuMp_6aobVi4,10758
|
542
|
+
sglang/srt/models/qwen2.py,sha256=ab912Yyk0aXOzI-wrxqN-sNF3bTVkNxB8P2uNcOCv9U,16394
|
543
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=uNnYhY8x-9H1GzUJkj7lUtR5d-0yMRNWUcT7-4qPlMU,22555
|
533
544
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
534
545
|
sglang/srt/models/qwen2_eagle.py,sha256=Iz0HWL2FgSD3FqoFhfYmbIZeEYkPTJ96lYbkncmHJX4,4644
|
535
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
546
|
+
sglang/srt/models/qwen2_moe.py,sha256=bmS2pyHD5zQo5plTCzAo_mjnahVtJ1jaRSURX1PlQC4,18313
|
536
547
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
537
|
-
sglang/srt/models/qwen2_vl.py,sha256=
|
548
|
+
sglang/srt/models/qwen2_vl.py,sha256=NCG85isoPkepv5RU-eLh44rCHPhfT3bu7pifNdBEsVw,21612
|
549
|
+
sglang/srt/models/qwen3.py,sha256=reaowGkotYAGHS5zTCWrvnyxtu92QKus19n-2amtMa4,12358
|
550
|
+
sglang/srt/models/qwen3_moe.py,sha256=Tee7oW6Xvo2pV_Q93y-HKykBFiPjo_-YfeIsIelB3hA,15623
|
538
551
|
sglang/srt/models/registry.py,sha256=inKh9iwOp3LFYm3nqujg-OtABClOP-ifc1stA9cZegA,3434
|
539
|
-
sglang/srt/models/stablelm.py,sha256=
|
552
|
+
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
540
553
|
sglang/srt/models/torch_native_llama.py,sha256=5tfFSMAXB3ScToqTALtCXa8Oo-qPCJh-KQCNB6QOlNA,19293
|
541
|
-
sglang/srt/models/xverse.py,sha256=
|
542
|
-
sglang/srt/models/xverse_moe.py,sha256=
|
554
|
+
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
555
|
+
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
543
556
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
544
|
-
sglang/srt/openai_api/adapter.py,sha256=
|
557
|
+
sglang/srt/openai_api/adapter.py,sha256=DaSU4Pri70s3ZeMHeVzsnKjd8dA9lx_HOmpVs1TEepo,72095
|
545
558
|
sglang/srt/openai_api/protocol.py,sha256=Y8PFFhLbzhpoERM6-WsTkm-ZuGcE-3tfenh9e-AC1vc,13374
|
546
559
|
sglang/srt/platforms/interface.py,sha256=hym3iooBB4C8if5hDZezgVN6h4NIOu7sg2ZUBIV6XmM,11246
|
547
560
|
sglang/srt/sampling/custom_logit_processor.py,sha256=tDvoLgLqn-sy1qcY6vSrpbnHCeqbdk0uhMOO-uy4p4E,1099
|
548
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
561
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=4LCowU2bk0TOSfIGpEy90N1SpTsiOKK8Rx1ZYcklUFQ,11988
|
549
562
|
sglang/srt/sampling/sampling_params.py,sha256=nXm44Inn91YtrMpAm5mDb6-97owRy-Bh6lZ0BIpw73I,5919
|
550
563
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
551
564
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
@@ -553,15 +566,15 @@ sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4T
|
|
553
566
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
554
567
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
555
568
|
sglang/srt/speculative/build_eagle_tree.py,sha256=SFQ3eHbhfNxOdxgqDP5wSV_ZlIVqLw7VivycNZ963N0,11690
|
556
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
557
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
558
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
569
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=FP-Dc6K4zaL2KQA8QsNccBM8TXnwREh1I2iPL9KHo8I,9252
|
570
|
+
sglang/srt/speculative/eagle_utils.py,sha256=mv--nBUgAbqP30pU3aGEMwQIHBwwevETUMQSZAelApE,28721
|
571
|
+
sglang/srt/speculative/eagle_worker.py,sha256=iQ7E6RLNyxXNs_jqbQ8SpdaXEMIC-ULBslrY9iMTv3g,26865
|
559
572
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
560
573
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
561
574
|
sglang/test/few_shot_gsm8k.py,sha256=7VLbWl4nCQs1wjtW4q-46jf9jUCycSs5Iw8v7sUSzBw,4284
|
562
575
|
sglang/test/few_shot_gsm8k_engine.py,sha256=QQbrwOX6-cJDD3RZC_e7zPnt6aSo8JdF8X_lRHSjdDM,3886
|
563
576
|
sglang/test/run_eval.py,sha256=9yO0hXZOcn4abEOs96T-XPguDEklK16Ltco0pGF3zCg,4020
|
564
|
-
sglang/test/runners.py,sha256=
|
577
|
+
sglang/test/runners.py,sha256=I2gXi0r663tvGlHLvh-W963Nv2yieA8MWVgwWe9zDbc,30656
|
565
578
|
sglang/test/send_one.py,sha256=6FhbJ3c8RpXxvFTELRXaF97GpT7zXXsCDYZh1DqG22E,2550
|
566
579
|
sglang/test/simple_eval_common.py,sha256=joqrGysuLnJFtzDRIgFkMsRyKUSyjVPFWp0_PHAL3Ik,12378
|
567
580
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
@@ -570,17 +583,19 @@ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWU
|
|
570
583
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
571
584
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
572
585
|
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
573
|
-
sglang/test/test_block_fp8.py,sha256=
|
586
|
+
sglang/test/test_block_fp8.py,sha256=3gOC4Xkxh2LXfT7T2aL8acWzpSdJlRdA3KlO0I1Wtkc,21594
|
574
587
|
sglang/test/test_block_fp8_ep.py,sha256=N1rvqbPErBaFFpeAw8TLYXGNZOoG7cfIBP2p5XbSyMo,10806
|
575
|
-
sglang/test/test_custom_ops.py,sha256=
|
588
|
+
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
576
589
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
577
590
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
578
591
|
sglang/test/test_programs.py,sha256=VZ3vXtUDBnXz0M7gFdDH8hXg9Wa0j_qI8CVqjEgRN_E,18877
|
579
|
-
sglang/test/test_utils.py,sha256=
|
592
|
+
sglang/test/test_utils.py,sha256=Y7XMx8-BTQJr6a90qRVpK4x9Lkl_p2WyL0VwFNHxhPs,30530
|
580
593
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
581
|
-
sglang/test/attention/test_flashattn_backend.py,sha256=
|
582
|
-
sglang
|
583
|
-
sglang
|
584
|
-
sglang-0.4.5.dist-info/
|
585
|
-
sglang-0.4.5.dist-info/
|
586
|
-
sglang-0.4.5.dist-info/
|
594
|
+
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
595
|
+
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
596
|
+
sglang/test/attention/test_prefix_chunk_info.py,sha256=er0i3KGHMkw-4UZB1GCFd4oYwRcXfU5wpO1ORqpNGGA,7626
|
597
|
+
sglang-0.4.5.post2.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
598
|
+
sglang-0.4.5.post2.dist-info/METADATA,sha256=C7YpNRcr_rgjjRxghmVgh_lQdH7BCAgvIZqNYLag3zU,25592
|
599
|
+
sglang-0.4.5.post2.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
|
600
|
+
sglang-0.4.5.post2.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
601
|
+
sglang-0.4.5.post2.dist-info/RECORD,,
|
sglang/lang/__init__.py
DELETED
File without changes
|