sglang 0.4.5.post1__py3-none-any.whl → 0.4.5.post3__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 +2 -2
- sglang/bench_serving.py +3 -6
- sglang/compile_deep_gemm.py +136 -0
- sglang/lang/backend/anthropic.py +0 -4
- sglang/lang/backend/base_backend.py +1 -1
- sglang/lang/backend/openai.py +6 -2
- sglang/lang/backend/runtime_endpoint.py +5 -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 +4 -1
- sglang/srt/constrained/outlines_jump_forward.py +14 -1
- 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/decode.py +105 -6
- sglang/srt/disaggregation/mini_lb.py +74 -9
- sglang/srt/disaggregation/mooncake/conn.py +33 -63
- sglang/srt/disaggregation/mooncake/transfer_engine.py +30 -61
- sglang/srt/disaggregation/nixl/__init__.py +1 -0
- sglang/srt/disaggregation/nixl/conn.py +622 -0
- sglang/srt/disaggregation/prefill.py +137 -17
- sglang/srt/disaggregation/utils.py +32 -0
- sglang/srt/entrypoints/engine.py +4 -0
- sglang/srt/entrypoints/http_server.py +3 -7
- sglang/srt/entrypoints/verl_engine.py +7 -5
- sglang/srt/function_call_parser.py +60 -0
- sglang/srt/layers/activation.py +6 -8
- sglang/srt/layers/attention/flashattention_backend.py +883 -209
- sglang/srt/layers/attention/flashinfer_backend.py +5 -2
- 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/double_sparsity_attention.py +5 -5
- sglang/srt/layers/attention/triton_ops/extend_attention.py +18 -7
- sglang/srt/layers/attention/triton_ops/prefill_attention.py +7 -3
- sglang/srt/layers/dp_attention.py +1 -1
- sglang/srt/layers/layernorm.py +20 -5
- sglang/srt/layers/linear.py +17 -3
- sglang/srt/layers/moe/ep_moe/layer.py +17 -29
- sglang/srt/layers/moe/fused_moe_native.py +4 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +14 -19
- sglang/srt/layers/moe/fused_moe_triton/layer.py +7 -0
- sglang/srt/layers/moe/topk.py +27 -30
- sglang/srt/layers/parameter.py +0 -2
- sglang/srt/layers/quantization/__init__.py +1 -0
- sglang/srt/layers/quantization/blockwise_int8.py +2 -0
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py +9 -2
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +16 -44
- sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py +2 -0
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +153 -0
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +4 -7
- sglang/srt/layers/quantization/deep_gemm.py +378 -0
- sglang/srt/layers/quantization/fp8.py +115 -132
- sglang/srt/layers/quantization/fp8_kernel.py +213 -88
- sglang/srt/layers/quantization/fp8_utils.py +189 -264
- sglang/srt/layers/quantization/gptq.py +13 -7
- sglang/srt/layers/quantization/modelopt_quant.py +2 -2
- sglang/srt/layers/quantization/moe_wna16.py +2 -0
- sglang/srt/layers/quantization/utils.py +5 -11
- sglang/srt/layers/quantization/w8a8_fp8.py +2 -0
- sglang/srt/layers/quantization/w8a8_int8.py +7 -7
- sglang/srt/layers/radix_attention.py +15 -0
- sglang/srt/layers/rotary_embedding.py +9 -8
- sglang/srt/layers/sampler.py +7 -12
- 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/data_parallel_controller.py +7 -1
- sglang/srt/managers/detokenizer_manager.py +0 -1
- sglang/srt/managers/io_struct.py +15 -3
- sglang/srt/managers/mm_utils.py +4 -3
- sglang/srt/managers/multimodal_processor.py +0 -2
- sglang/srt/managers/multimodal_processors/base_processor.py +3 -2
- sglang/srt/managers/schedule_batch.py +15 -4
- sglang/srt/managers/scheduler.py +28 -77
- sglang/srt/managers/tokenizer_manager.py +116 -29
- sglang/srt/managers/tp_worker.py +1 -0
- sglang/srt/mem_cache/hiradix_cache.py +41 -29
- sglang/srt/mem_cache/memory_pool.py +38 -15
- sglang/srt/model_executor/cuda_graph_runner.py +15 -10
- sglang/srt/model_executor/model_runner.py +39 -31
- sglang/srt/models/bert.py +398 -0
- sglang/srt/models/deepseek.py +1 -1
- sglang/srt/models/deepseek_nextn.py +74 -70
- sglang/srt/models/deepseek_v2.py +292 -348
- sglang/srt/models/llama.py +5 -5
- sglang/srt/models/minicpm3.py +31 -203
- sglang/srt/models/minicpmo.py +17 -6
- sglang/srt/models/qwen2.py +4 -1
- sglang/srt/models/qwen2_moe.py +14 -13
- sglang/srt/models/qwen3.py +335 -0
- sglang/srt/models/qwen3_moe.py +423 -0
- sglang/srt/openai_api/adapter.py +71 -4
- sglang/srt/openai_api/protocol.py +6 -1
- sglang/srt/reasoning_parser.py +0 -1
- sglang/srt/sampling/sampling_batch_info.py +2 -3
- sglang/srt/server_args.py +86 -72
- sglang/srt/speculative/build_eagle_tree.py +2 -2
- sglang/srt/speculative/eagle_utils.py +2 -2
- sglang/srt/speculative/eagle_worker.py +6 -14
- sglang/srt/utils.py +62 -6
- sglang/test/runners.py +5 -1
- sglang/test/test_block_fp8.py +167 -0
- sglang/test/test_custom_ops.py +1 -1
- sglang/test/test_utils.py +3 -1
- sglang/version.py +1 -1
- {sglang-0.4.5.post1.dist-info → sglang-0.4.5.post3.dist-info}/METADATA +5 -5
- {sglang-0.4.5.post1.dist-info → sglang-0.4.5.post3.dist-info}/RECORD +116 -110
- {sglang-0.4.5.post1.dist-info → sglang-0.4.5.post3.dist-info}/WHEEL +1 -1
- sglang/lang/__init__.py +0 -0
- sglang/srt/lora/backend/__init__.py +0 -25
- sglang/srt/server.py +0 -18
- {sglang-0.4.5.post1.dist-info → sglang-0.4.5.post3.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.5.post1.dist-info → sglang-0.4.5.post3.dist-info}/top_level.txt +0 -0
@@ -1,44 +1,43 @@
|
|
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=uTFldXFCArLc6J-ezjHFdM9TsoA9q6nfrjYAGsq5cwY,57582
|
7
7
|
sglang/check_env.py,sha256=76itNLUw9KlqbiY1BI4u4YaMZaqyCNcrCLUIb6aHflM,8396
|
8
|
+
sglang/compile_deep_gemm.py,sha256=95dhv7JDz-1cYgO0foLflvc7uDsW3EdaPtJ5Ty-BcHs,4367
|
8
9
|
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
9
10
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
10
11
|
sglang/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
11
12
|
sglang/utils.py,sha256=GIcgiRHkZ-gyPxXOdn1qFF41jkg4-YdDxbPc4mzO-qk,16159
|
12
|
-
sglang/version.py,sha256=
|
13
|
-
sglang/lang/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
13
|
+
sglang/version.py,sha256=qJn6r7BVBDslRB6U_6hE4TM-HRFrJeQvVYrIxenjcs0,28
|
14
14
|
sglang/lang/chat_template.py,sha256=MwNL5dNTe8g_l2ljZubnrazEgT2xEv-9O2D0Ezwxy4I,19658
|
15
15
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
16
|
-
sglang/lang/compiler.py,sha256=
|
16
|
+
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
17
17
|
sglang/lang/interpreter.py,sha256=OH1SFCm4rUCPO32MTo8j5V2Z13Jic7_r1GQOP1-aHaw,33234
|
18
18
|
sglang/lang/ir.py,sha256=gssBGxqQEVJmjR_PqG2yah48AsInGaO3CmnQ2boJThc,18769
|
19
|
-
sglang/lang/tracer.py,sha256=
|
19
|
+
sglang/lang/tracer.py,sha256=20B9w2W3d0D6xSUGZjKFszFuZAzsa3gvgdIgsXR8GtU,8176
|
20
20
|
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=
|
21
|
+
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
22
|
+
sglang/lang/backend/base_backend.py,sha256=tEutGCU5tni1xGlrIjAVvA9aflJBt2duKrIDzqabJWc,1975
|
23
23
|
sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
|
24
|
-
sglang/lang/backend/openai.py,sha256=
|
25
|
-
sglang/lang/backend/runtime_endpoint.py,sha256=
|
26
|
-
sglang/lang/backend/vertexai.py,sha256=
|
27
|
-
sglang/srt/_custom_ops.py,sha256=
|
24
|
+
sglang/lang/backend/openai.py,sha256=YFs7pCDK6_DoYmjTa-vgDVdaeE4PYr7E-sIC1q7vAns,16422
|
25
|
+
sglang/lang/backend/runtime_endpoint.py,sha256=4pTG1TnOVTWBCh3rMhqL_NP2hsawG9xuPpuDuUFvD6A,16882
|
26
|
+
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
27
|
+
sglang/srt/_custom_ops.py,sha256=L7NuEaRD_Q6Q54n0NZnLXgWZURbnn8Tkg4NQedE6zgA,3616
|
28
28
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
29
29
|
sglang/srt/code_completion_parser.py,sha256=HhEUzdL-FVBsOot9tKDKA1l8Gdx8qsF1RRg-zHNpmLQ,5400
|
30
30
|
sglang/srt/conversation.py,sha256=WP72AZrZpiqc5RowucT2tW3jVCb1pb4veW_kpwYS4yY,28785
|
31
|
-
sglang/srt/custom_op.py,sha256=
|
32
|
-
sglang/srt/function_call_parser.py,sha256=
|
31
|
+
sglang/srt/custom_op.py,sha256=J1PUcGaeJJjfAjp06BQsLpUkKyR1zsh9MvDiDlqqJsg,1129
|
32
|
+
sglang/srt/function_call_parser.py,sha256=7RSiI3QSzQagB1TZEHxRI7FU0saiL3SNedxlfDP42O0,26760
|
33
33
|
sglang/srt/hf_transformers_utils.py,sha256=N2f-gA8yUq-UP_TJT276gNbDNzmddWsmWnq3px6TIj8,9342
|
34
34
|
sglang/srt/mm_utils.py,sha256=1ScBunw_x4W8ebM_AcJ62-1T2mfT8NlMJqdAhkF1lb0,12367
|
35
35
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
36
36
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
37
|
-
sglang/srt/reasoning_parser.py,sha256=
|
38
|
-
sglang/srt/
|
39
|
-
sglang/srt/server_args.py,sha256=k42YCDTbEEZZShmoaorQGNRwMxYACDSpvGW2toTb2DQ,53778
|
37
|
+
sglang/srt/reasoning_parser.py,sha256=JnaEVW0KG1yJpn9uxmrjwErb9imzni05QDFjExryoqM,5584
|
38
|
+
sglang/srt/server_args.py,sha256=pd2vozUFro4apc72-GzTuMINMRZI6tYBfrkxD4uvWcw,54951
|
40
39
|
sglang/srt/torch_memory_saver_adapter.py,sha256=KG3wM9-xZsSdsmORofArnNR7hH55GEyFxaderCDcK9w,1853
|
41
|
-
sglang/srt/utils.py,sha256=
|
40
|
+
sglang/srt/utils.py,sha256=2BRFNpnDtnFbYHCUClPlPFY6tYsXDaXFDzmpEID1yjg,62903
|
42
41
|
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
43
42
|
sglang/srt/configs/__init__.py,sha256=vulncVn70WqIT6s0HaB8p_Q6FjOiaLwNZWpoJS9FIuQ,399
|
44
43
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
@@ -48,7 +47,7 @@ sglang/srt/configs/device_config.py,sha256=kfmpPOECqYxcRoY-ko0QZRhyiBWUGP2CMF51D
|
|
48
47
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
49
48
|
sglang/srt/configs/janus_pro.py,sha256=-QtJ4ZGZiAJb0AkOEcuCHzIKLw23nF8nRk3rdCcoUO0,19016
|
50
49
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
51
|
-
sglang/srt/configs/model_config.py,sha256=
|
50
|
+
sglang/srt/configs/model_config.py,sha256=UXQZnETXzJVU4BJz-RCDBfIBEke41El_vl1K7f3dmCs,22199
|
52
51
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
53
52
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
54
53
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -61,18 +60,21 @@ sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOU
|
|
61
60
|
sglang/srt/constrained/base_grammar_backend.py,sha256=ljTVWpBo3bolce-E_-mtHIY2XWez4qcyDPeaIeZyIhM,7454
|
62
61
|
sglang/srt/constrained/llguidance_backend.py,sha256=Kgd-PQVBQlKWsz506OpF_xSdNBhEbvFywzICTZg21iM,5729
|
63
62
|
sglang/srt/constrained/outlines_backend.py,sha256=XbmkZSJzJnnY7k11uj8Et3StfuOiFwRs3ID4IRYAA4Q,6839
|
64
|
-
sglang/srt/constrained/outlines_jump_forward.py,sha256=
|
63
|
+
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
65
64
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=XFxdZqvPofmtCeIMqR10NOyph06HwbdXfiVI8rIoV5s,3646
|
66
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=
|
67
|
-
sglang/srt/
|
68
|
-
sglang/srt/disaggregation/
|
69
|
-
sglang/srt/disaggregation/
|
70
|
-
sglang/srt/disaggregation/
|
65
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=oc3BTTe8mB5Szv_O-5nZzWbKEKFb22oUniqTUZhewLQ,7409
|
66
|
+
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
67
|
+
sglang/srt/disaggregation/decode.py,sha256=FbUKa3qiCGGqRzz5rJiNQMqIFhFj4BXONYRfH80PteA,22812
|
68
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=1YTFUV5ovVf_D2RXmvyn21x9kVgH8x2RmmRY3mSOfZI,9630
|
69
|
+
sglang/srt/disaggregation/prefill.py,sha256=1MoGATkj89vv9_eBHcMGxAQiyxnow1idvL_IjudjV0o,14615
|
70
|
+
sglang/srt/disaggregation/utils.py,sha256=6ackrcitNF94ur9bRvPerF29E7g8uU_0a4-nSdw1EMs,3078
|
71
71
|
sglang/srt/disaggregation/base/__init__.py,sha256=KR8xXoRCDAy2U623mfP6ujXu42m1_F9EiudjrKu2I_A,130
|
72
72
|
sglang/srt/disaggregation/base/conn.py,sha256=gpf32bhYXWm_iaYB6WcrDaJ-UoL1ZzPI_xpi5pMhRQo,2443
|
73
73
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=1vacEHmWjf7zgbMPzsXKB08FqNKNCquJdUiDlO41BOk,122
|
74
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
75
|
-
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=
|
74
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=3byp9qhu9fCcv1_HAK-P0fZB6_o3sC6Qq_i0tbLItkM,21250
|
75
|
+
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=MxDAB9ZetRF1pFS2LP3FVHPtQ1HjIt_SK3UMaYHZ94o,2604
|
76
|
+
sglang/srt/disaggregation/nixl/__init__.py,sha256=n9HjrRk36WUcZNeetGWOh2pSriLp7GNTq7YYX9K3EtY,85
|
77
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=ZFyKZQtGrTw7lNi9BYNlfY-1idHFzerTfvVNHG2Uj5c,22652
|
76
78
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
77
79
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
78
80
|
sglang/srt/distributed/parallel_state.py,sha256=hoTgLYfHIKMb_tSwBTauuusJZ8oY9BsiubTTOF8UfIw,50713
|
@@ -86,48 +88,48 @@ sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6
|
|
86
88
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=bbruDIM1GgKIdB6gi71_I0mpB179I-qyvwKuSj1Kaic,20816
|
87
89
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
88
90
|
sglang/srt/entrypoints/EngineBase.py,sha256=xoyvp6XAeDLY2_Q2Ng33H-fRhrXHv2ldJJKd-HuDhqE,1870
|
89
|
-
sglang/srt/entrypoints/engine.py,sha256
|
90
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
91
|
+
sglang/srt/entrypoints/engine.py,sha256=-qHfYFDremLj8GhwQa7GuWHQKop7Tyq2HvmBXULtCos,22282
|
92
|
+
sglang/srt/entrypoints/http_server.py,sha256=vhrkH8N0Vc8xwaRkNsz13ptQ2uRnrZ8ggkOiC_bhW70,28353
|
91
93
|
sglang/srt/entrypoints/http_server_engine.py,sha256=ihA6y3GXRs28Y9U3SgdQcJQjnw_SVIby7QrVgiafX04,4846
|
92
|
-
sglang/srt/entrypoints/verl_engine.py,sha256=
|
93
|
-
sglang/srt/layers/activation.py,sha256=
|
94
|
-
sglang/srt/layers/dp_attention.py,sha256=
|
94
|
+
sglang/srt/entrypoints/verl_engine.py,sha256=XLYdwTwhH0jTjw8xczgZXWfBXMRb_ur2bg4TN0dTwfI,6975
|
95
|
+
sglang/srt/layers/activation.py,sha256=oSkdo8B8najXFcVay3Y__CEvgXh87lAIhG0CMp2Ugqs,5954
|
96
|
+
sglang/srt/layers/dp_attention.py,sha256=WJgXg_KyBzDHkwyfUFBowpDRFd0q5Q9LgEhqT-qT_ys,7549
|
95
97
|
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
96
|
-
sglang/srt/layers/layernorm.py,sha256=
|
97
|
-
sglang/srt/layers/linear.py,sha256=
|
98
|
+
sglang/srt/layers/layernorm.py,sha256=H5hD0OPHNeNBKkJcFsm3unOERJBNe-s1en4S3GAILzI,4936
|
99
|
+
sglang/srt/layers/linear.py,sha256=nC9MxJrFap1BEyqgFlBySH4IeQruIbcBp32cOhUl5Fw,52149
|
98
100
|
sglang/srt/layers/logits_processor.py,sha256=Vp8ibljVEezTr54xzeOcjiJR7JdYO8ItkO5nLIIMVu0,24206
|
99
|
-
sglang/srt/layers/parameter.py,sha256=
|
101
|
+
sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
|
100
102
|
sglang/srt/layers/pooler.py,sha256=rj2lygvleBnyLCBZ8I11HGMgpfIDsT0l3PIkshJwdu4,1606
|
101
|
-
sglang/srt/layers/radix_attention.py,sha256=
|
102
|
-
sglang/srt/layers/rotary_embedding.py,sha256=
|
103
|
-
sglang/srt/layers/sampler.py,sha256=
|
103
|
+
sglang/srt/layers/radix_attention.py,sha256=xcsEmKLZYu7K3RaYnMX67H86XLiKD8AGu0Ob-4oV8aU,3247
|
104
|
+
sglang/srt/layers/rotary_embedding.py,sha256=voz9dM_9f6uVww9FuaUkwYDFJ_U0r_dXsdv-MaWvX18,45705
|
105
|
+
sglang/srt/layers/sampler.py,sha256=PNgMXm2vsNsE6Rt89R5GLDC3lDxdIujoWli8F3vldng,11384
|
104
106
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
105
107
|
sglang/srt/layers/vocab_parallel_embedding.py,sha256=QUxd4sELx6p3dHvEKmccPZ-phdd_9EjNdwjH3SJ9zxI,22238
|
106
108
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=X_GIbQuU9njtUEGdUP7E_KRhmGxj3UyPHNESlL3QaQ8,3264
|
107
109
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
108
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
109
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
110
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=YEWvK6Q3KsCH3YLbLZ8k2IAN1U_vvvLlZ9wE9aZKxBU,82342
|
111
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=YtMTgMhxxNrAbSoWTPJczgY4SR3WjnAPXPoJ2d5PUZY,46394
|
110
112
|
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=pnVhvVEK87iFW8gUb1G7X7c1tqro8R2DSEOFCnlV8Bo,30301
|
111
113
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=1RPFNtQOBw6BWxIjrzfJgA9Nx92udLbR-S5KXmqjxS8,10536
|
112
|
-
sglang/srt/layers/attention/torch_native_backend.py,sha256=
|
113
|
-
sglang/srt/layers/attention/triton_backend.py,sha256=
|
114
|
+
sglang/srt/layers/attention/torch_native_backend.py,sha256=K5hUqBgakk2COSQqsaxWs0yEVOHS-7BlOygZTOeI8kE,9444
|
115
|
+
sglang/srt/layers/attention/triton_backend.py,sha256=oEEiUwHbm4rNw5ExbQ2c3n0TwAgkk77yuLFenj9bHOo,26902
|
114
116
|
sglang/srt/layers/attention/utils.py,sha256=J9mA-cbZT3uTlaKXo0HEAaeMei_TS2o4McTna9LVDCE,2750
|
115
117
|
sglang/srt/layers/attention/vision.py,sha256=H7dQofAlZjC48Dr6bo4HBsZSLDhdrbHKChyGejeaEGo,11886
|
116
118
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=DPu_aCPgwPqKWZPEQmp_xA7MPbpV2ip-MEICCB470Ao,19120
|
117
|
-
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=
|
118
|
-
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=
|
119
|
-
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=
|
119
|
+
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=vsDZZ5QGb8-KBzADgKshnVQbsW8zRJF1h5hgdPGW5lU,31124
|
120
|
+
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=m12jEnQkNJguATqvZ57HtMC2hhU4wqdB8xAYdh25BxE,13922
|
121
|
+
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
120
122
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
121
|
-
sglang/srt/layers/moe/fused_moe_native.py,sha256=
|
123
|
+
sglang/srt/layers/moe/fused_moe_native.py,sha256=IWoRLIEMhXH8KAB9jt5QSnhUtHn4SnbJ9dDO1LNTZ9o,4659
|
122
124
|
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
123
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
125
|
+
sglang/srt/layers/moe/topk.py,sha256=K-VU64nWBV07bu1Okn-uYbhz9gylq-KFNRYn2SFzu28,11129
|
124
126
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
125
127
|
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=ijqRzS-tb0LGnDU5hW-g0JH104ppADrWaUIDGxb9Feo,22919
|
126
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
128
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=SZ0shPwgDp7xj-TCv9bfg5O7f2AXjF6xmBP5xkZ0Ips,36440
|
127
129
|
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=zQV7Qr-Zrcr3D3efVvZepRQM02bj5djHPsijPssavk8,20430
|
128
130
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
129
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
130
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
131
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=DRkGQ6vuk4d786_UWMBqYlw-9o75k-T_rdtLQLZldK4,55410
|
132
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=XofcceHnkmqhVczEIVqGSbsxps5LiYTGcaCk1Say9YM,24951
|
131
133
|
"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
|
132
134
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
133
135
|
"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
|
@@ -262,29 +264,31 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=43-UL9KEMoaiC0cRSzWFbg2PA
|
|
262
264
|
"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
|
263
265
|
"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
|
264
266
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Uz5X80VcNBOaxshwVNUEittHk2zqB4HQCfTJ4TPG5aM,3274
|
265
|
-
sglang/srt/layers/quantization/__init__.py,sha256=
|
267
|
+
sglang/srt/layers/quantization/__init__.py,sha256=UOQcyCvKFkX0u_OPPex7X5X98iUR3lXgBnLbffu0n9g,12424
|
266
268
|
sglang/srt/layers/quantization/awq.py,sha256=VImnVCU_QBLFba6S88T0dJ-vLy6SMm3OLIMEdllDfVI,6663
|
267
269
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
268
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=
|
269
|
-
sglang/srt/layers/quantization/
|
270
|
-
sglang/srt/layers/quantization/
|
271
|
-
sglang/srt/layers/quantization/
|
272
|
-
sglang/srt/layers/quantization/
|
270
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=cu9-JiCZDfMfvB97Kv_-eEG87VX5bRFIllFkzpO_xIg,15122
|
271
|
+
sglang/srt/layers/quantization/deep_gemm.py,sha256=xYDc5nh2nD2R_Apw0r4Swd3IYDzk3MGo8xlkV3W-Xl4,12800
|
272
|
+
sglang/srt/layers/quantization/fp8.py,sha256=Niu89OfZd4pIpkwZ1zd2Hrlffx0c5L5zkix6Lzi0Vys,40970
|
273
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=C2_hOLRO27-Yvjy-Nm2niehD2gWSMuP6TnNX07ESqh4,32018
|
274
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=1AmKsAFlpPcwbqpFR6P2CaCOvpp8dYY7lzXLoKjVikE,18631
|
275
|
+
sglang/srt/layers/quantization/gptq.py,sha256=gyGMOPXHzozK7pPWSjKgLdFX9h7MCEww7n8FqEVEVac,15364
|
273
276
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRn_imIw8kNgqdtb2lr7BettjgDgimbl1Rubnamjh8,11352
|
274
277
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
275
278
|
sglang/srt/layers/quantization/kv_cache.py,sha256=-yaFTdB75T0BbvQeuIpH6rZoL3R8t6OIJVGB-xdtpCw,3492
|
276
|
-
sglang/srt/layers/quantization/modelopt_quant.py,sha256=
|
277
|
-
sglang/srt/layers/quantization/moe_wna16.py,sha256=
|
278
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
279
|
-
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=
|
280
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
279
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=TpPgtbV7O5r1JY4Wm0np2pReQO6XERIdEDQcV41oTn0,16596
|
280
|
+
sglang/srt/layers/quantization/moe_wna16.py,sha256=KtFr4lIslMA12yx4JjXXPOsa5OHjxXWA6scYCRQnFMQ,19483
|
281
|
+
sglang/srt/layers/quantization/utils.py,sha256=3fP11UCSWkFWW7oTfQ6_3I1ZXfHvRL4WIlTAXnT1Ues,5442
|
282
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=VhM36MKz02W3uPCi-9Ap0XpQPXBdL88ny3l_aEtUq2M,11766
|
283
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=MkvmcxQj3X5AZbx8pgnHYAikc_Xd_jOhJXaxx7255ho,8984
|
281
284
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
282
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=
|
283
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
285
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EaOKuIA0zXwqmH_eVhWeNdGJT9d1d9gVvFyYkgpdjDg,25665
|
286
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=no7gs-M8eEYvNd0XPoVudfb1mBweoSFfcHYoWytJeAY,26199
|
284
287
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
285
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=
|
288
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
286
289
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
287
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/
|
290
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=-iq634sU38yWFA-h3w-B4kTALeXMo7uRZQI6CckMZTo,5494
|
291
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=NZurhURFpZKqfMfgyd7oHLTLThm_8AO7xBCY8F6i3Gk,5881
|
288
292
|
"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
|
289
293
|
"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
|
290
294
|
"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
|
@@ -437,16 +441,15 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
437
441
|
"sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
438
442
|
"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
|
439
443
|
"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
|
440
|
-
sglang/srt/lora/layers.py,sha256=
|
441
|
-
sglang/srt/lora/lora.py,sha256=
|
444
|
+
sglang/srt/lora/layers.py,sha256=cu1kqDCuH05ck8HVtwmVuMVBzcPJZeDY3mk486teB4E,11848
|
445
|
+
sglang/srt/lora/lora.py,sha256=uNvbjZ_Wr1SLI9-ElRJA_JKwkibSGroP5Bfpsr9MI-Y,7527
|
442
446
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
443
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
447
|
+
sglang/srt/lora/lora_manager.py,sha256=nyqkm7RLoQE6myfqcH9r0zwME4aEZ3pFkVjY36QTlvA,9200
|
444
448
|
sglang/srt/lora/mem_pool.py,sha256=xUFoHUDJgX9lt2YugD9HUY5tIMnJiazYMZ6LYqSGv-E,9633
|
445
449
|
sglang/srt/lora/utils.py,sha256=GjEBgsGhDhX4NqVqeaciznQ8RotKZmb2c-nw4YMLHxA,5251
|
446
|
-
sglang/srt/lora/backend/
|
447
|
-
sglang/srt/lora/backend/
|
448
|
-
sglang/srt/lora/backend/
|
449
|
-
sglang/srt/lora/backend/triton_backend.py,sha256=_QbqggFPHMPWgx3PI15yyyfxBCTxSpGA209x_frI12E,2517
|
450
|
+
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
451
|
+
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
452
|
+
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
450
453
|
sglang/srt/lora/triton_ops/__init__.py,sha256=JGOYPIn1XbGcyJTbt8A0qoc02PYONSGNNjGkC8yJpAM,283
|
451
454
|
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=CDGt7lpu9GjykgMtmwbZ3PEqjTlRYyh28AUlj1cRcmw,5279
|
452
455
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=HTfU3HxxxVyaG_aJrrVjPJTnqf62yvepcKJKYkG0XJQ,5944
|
@@ -454,22 +457,22 @@ sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=ZmWEqHJaorRNNj-c_ZXPi_pX8X_yIA
|
|
454
457
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=Q58UzWUb3QFqY_ZxWA3poN373N0Hwkks5AQRKIuvFC8,4517
|
455
458
|
sglang/srt/managers/cache_controller.py,sha256=d4RGqbut1FlzJnpqr7WY_TYmRjYPS07OoOVbztjs5xI,18959
|
456
459
|
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
457
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=
|
458
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
460
|
+
sglang/srt/managers/data_parallel_controller.py,sha256=yKP4Emi5gEGIj5Z6jq2WZ-hRsPSXIb_tVnoYOx4g_pI,10583
|
461
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=3S3aRvKSi75RQSxEEQkeyxKDNNunWiw9wlwsbT1VXSo,10099
|
459
462
|
sglang/srt/managers/expert_distribution.py,sha256=r3o5RGI0gnV7xb60AApqKYa0oiSB37oB7hQBX7P3xZM,3225
|
460
|
-
sglang/srt/managers/io_struct.py,sha256=
|
461
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
462
|
-
sglang/srt/managers/multimodal_processor.py,sha256=
|
463
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
463
|
+
sglang/srt/managers/io_struct.py,sha256=K4ciMrIREZ7RbuhLeaxYrythW3JL9NJ3uzyAOKATk54,31252
|
464
|
+
sglang/srt/managers/mm_utils.py,sha256=P-UbCdzasK0yR-xn6Lrk3ILct3uJrIBuXSDrtRZlB_A,15542
|
465
|
+
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
466
|
+
sglang/srt/managers/schedule_batch.py,sha256=Kn5dP1Q8fiRRkCMQ29u0vJ49EV2f8cv3Rmx8hAuC_FI,63112
|
464
467
|
sglang/srt/managers/schedule_policy.py,sha256=E1qVq2G3jptKdX9nlqfayeRBUll9xB6bK8nBf3EW32E,19469
|
465
|
-
sglang/srt/managers/scheduler.py,sha256=
|
468
|
+
sglang/srt/managers/scheduler.py,sha256=BfobLcO8xH4PuLGGEJeDn5qinBEUws7_PofULNfC7f8,80361
|
466
469
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=u2sj6MViFTov0lVZSysZ-wph2pEqRCtCjwA1UdttZ7I,26338
|
467
470
|
sglang/srt/managers/session_controller.py,sha256=o-ifit0n4_xHLNmyD0Ams8FxGRgxFybX-Vz1hwgr3UQ,5755
|
468
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
469
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
471
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=dTD1lgPOJ6aBcxeT2eg_ZzQELgbdmYmIOmApTiiTpWU,50553
|
472
|
+
sglang/srt/managers/tp_worker.py,sha256=OV0Zc-oK-HXSWO6x26ItDEf-qB2IqyJq2z0TFuBZz0s,8970
|
470
473
|
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=3_ZJ8Rq7v2ZDaRNTRu5Dy8AbqiAlJQp3IAKnn_WAwd8,9127
|
471
474
|
sglang/srt/managers/utils.py,sha256=5i75uLlQOF_5CaT02CrWtwozMTtwTg2_nLP8Dtr-JZQ,1536
|
472
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=
|
475
|
+
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=M36x_Emm-IdpFiQpii3qyQZ79O7NZsyJgDT5gk08Plo,9923
|
473
476
|
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
474
477
|
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=j7j1D38azudJjYthVpdz7jxQ9Z7SjwQfskpOIshAdiY,3147
|
475
478
|
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=UlkyIoc8XOw69iFBYiBYLx--pdfnM4JfCFtwRrd3w-o,2267
|
@@ -482,28 +485,29 @@ sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=67EmFiAkvZncU-eqiiS0
|
|
482
485
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=NY62Zo0A0tLJ7ObRLOQqQcXCxoJUDZsK8f5U4dNQjKc,973
|
483
486
|
sglang/srt/mem_cache/chunk_cache.py,sha256=it5SfL1FwMbrdeOH-I-Eu_i-I9hFB1xL-z_brIUoCkk,1835
|
484
487
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
485
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
486
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
488
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=BJR-R2u5YyYIhGIxTY-3rf8Vx60XjCRU8Yhmkn2fzzM,16597
|
489
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=wexD6ojsN1tT_jtIa5uRU7UIPa6V0Zg1KNKJAa09aww,32338
|
487
490
|
sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
|
488
491
|
sglang/srt/mem_cache/radix_cache.py,sha256=Lm-pco6CJ4orb9IfDpbHm5MnyK8Ya0OF1x9p88dv548,14906
|
489
492
|
sglang/srt/metrics/collector.py,sha256=zHg4twFQJvuK1mSme3-EYQa9PJryfp_u7a4RxQ5RcO0,8874
|
490
493
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
491
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
494
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=lGnVuRqm7f34q79gvCbXoHCQcZyK14Xq_hXzWLP9cjs,23550
|
492
495
|
sglang/srt/model_executor/forward_batch_info.py,sha256=_qSMTiLxvcPIIgqRfUqG4W--OoirVY7ulcFfZqQIqjo,28689
|
493
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
496
|
+
sglang/srt/model_executor/model_runner.py,sha256=nOyU8BQmQz6Y67HS2D3AcA41mABtjeAYH8xVgjLoFdI,47104
|
494
497
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
495
498
|
sglang/srt/model_loader/loader.py,sha256=YYmtvkQw0B1qgPw0_gN-K4yy7CEYbTSR__0Dl1Fnm6k,55342
|
496
499
|
sglang/srt/model_loader/utils.py,sha256=0NaMR67fESFopaklmsleiL27XH1QUrjZW246MUu1EJ0,1369
|
497
500
|
sglang/srt/model_loader/weight_utils.py,sha256=yKnau-wH9muczoCpDTCVIqXFqz-QJmEEySplX3bMJWk,32153
|
498
501
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
502
|
+
sglang/srt/models/bert.py,sha256=kHlErDgNX_mIhfWWCnAcH_ncvYg22Y61gI34gW8GuUY,12738
|
499
503
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
500
504
|
sglang/srt/models/clip.py,sha256=fCMtAcaKjruSIWfD4YGb4HXh6Tzp2pjpgDmp5JpwBPU,19794
|
501
505
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
502
506
|
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
503
|
-
sglang/srt/models/deepseek.py,sha256=
|
507
|
+
sglang/srt/models/deepseek.py,sha256=m8CjJIJiQ9B_ACPy7dwMLfm4kVLXcuW27zDk_lcQ_Dc,16920
|
504
508
|
sglang/srt/models/deepseek_janus_pro.py,sha256=8wAzvcGdyo--3faMN4QtagT1eAZMhMFduvpCXqUS48Q,70456
|
505
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
506
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
509
|
+
sglang/srt/models/deepseek_nextn.py,sha256=mL2nnblFmeBD8cSf15BmJh_M-8dyCx07sqlicw4rab4,13454
|
510
|
+
sglang/srt/models/deepseek_v2.py,sha256=0GERrciRWktKyIwscFA0HPvm_XdElXxaEpJ0kY3SoGw,68497
|
507
511
|
sglang/srt/models/deepseek_vl2.py,sha256=RVvi_3qsfrkqMCCnjjTA8OwUc5ySutc7asAH-rUJLVo,12922
|
508
512
|
sglang/srt/models/exaone.py,sha256=rX7J0xFt9TSt6tMIhnYMkb5KDnqTJIV4BtjPLFwQ8_8,13425
|
509
513
|
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
@@ -517,7 +521,7 @@ sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,
|
|
517
521
|
sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,28033
|
518
522
|
sglang/srt/models/internlm2.py,sha256=RDAT9drjdgVEFmCMq99RTn3weMQFhl1NHhkhyDX8f7M,13056
|
519
523
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
520
|
-
sglang/srt/models/llama.py,sha256=
|
524
|
+
sglang/srt/models/llama.py,sha256=Y4ROe8ohP84G4vin_Sr_vjG0XRoM5gGgnrojxOXn_uc,24942
|
521
525
|
sglang/srt/models/llama4.py,sha256=JIVS5Q1lnmEpAHDI487gKO_9xfTCehSpzInNQeCg8JU,17940
|
522
526
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
523
527
|
sglang/srt/models/llama_eagle.py,sha256=OB2lKsjn7BcfCZljklnhk83me8j0PuQmYLou7baNcq4,4866
|
@@ -527,8 +531,8 @@ sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZe
|
|
527
531
|
sglang/srt/models/llava.py,sha256=KMwNNrlMuMaKEOZMDRBKBQbe6uctpKTLc0zOceyGC34,27242
|
528
532
|
sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc,12829
|
529
533
|
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
530
|
-
sglang/srt/models/minicpm3.py,sha256=
|
531
|
-
sglang/srt/models/minicpmo.py,sha256=
|
534
|
+
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
535
|
+
sglang/srt/models/minicpmo.py,sha256=qSs4c8aOU1W_V4fDYtcboWKFPF06NIw-h9rWozob7JQ,76204
|
532
536
|
sglang/srt/models/minicpmv.py,sha256=79zZn3co9r7SERatx49EuHRoLWRiy6qeaUFgjDWJo2I,40571
|
533
537
|
sglang/srt/models/mistral.py,sha256=EYifJUUzN2Z2-iL37eJiNZF_DB0H4pa0mKlgYRIxM70,838
|
534
538
|
sglang/srt/models/mixtral.py,sha256=zQHCL_ZMKmLR7jitpEw8n7Rv6xhxUJzSXklsw6auh2E,14965
|
@@ -540,40 +544,42 @@ sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14
|
|
540
544
|
sglang/srt/models/olmoe.py,sha256=TMzt-yB891bvA4X50xL0NjNnFYSx9imlA7N1EG8KNK0,15949
|
541
545
|
sglang/srt/models/phi3_small.py,sha256=UbqZvpwWolXUPd0zbKgbL93yVXUY1n4kXJLgIe_gjaM,15508
|
542
546
|
sglang/srt/models/qwen.py,sha256=xYkVmMZS2uMqWhfndc8EYm0olpKFnggfuMp_6aobVi4,10758
|
543
|
-
sglang/srt/models/qwen2.py,sha256=
|
547
|
+
sglang/srt/models/qwen2.py,sha256=ab912Yyk0aXOzI-wrxqN-sNF3bTVkNxB8P2uNcOCv9U,16394
|
544
548
|
sglang/srt/models/qwen2_5_vl.py,sha256=uNnYhY8x-9H1GzUJkj7lUtR5d-0yMRNWUcT7-4qPlMU,22555
|
545
549
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
546
550
|
sglang/srt/models/qwen2_eagle.py,sha256=Iz0HWL2FgSD3FqoFhfYmbIZeEYkPTJ96lYbkncmHJX4,4644
|
547
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
551
|
+
sglang/srt/models/qwen2_moe.py,sha256=bmS2pyHD5zQo5plTCzAo_mjnahVtJ1jaRSURX1PlQC4,18313
|
548
552
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
549
553
|
sglang/srt/models/qwen2_vl.py,sha256=NCG85isoPkepv5RU-eLh44rCHPhfT3bu7pifNdBEsVw,21612
|
554
|
+
sglang/srt/models/qwen3.py,sha256=reaowGkotYAGHS5zTCWrvnyxtu92QKus19n-2amtMa4,12358
|
555
|
+
sglang/srt/models/qwen3_moe.py,sha256=Tee7oW6Xvo2pV_Q93y-HKykBFiPjo_-YfeIsIelB3hA,15623
|
550
556
|
sglang/srt/models/registry.py,sha256=inKh9iwOp3LFYm3nqujg-OtABClOP-ifc1stA9cZegA,3434
|
551
557
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
552
558
|
sglang/srt/models/torch_native_llama.py,sha256=5tfFSMAXB3ScToqTALtCXa8Oo-qPCJh-KQCNB6QOlNA,19293
|
553
559
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
554
560
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
555
561
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
556
|
-
sglang/srt/openai_api/adapter.py,sha256=
|
557
|
-
sglang/srt/openai_api/protocol.py,sha256=
|
562
|
+
sglang/srt/openai_api/adapter.py,sha256=t5SqWVLz3ASJx_b8K8JkjXcq7qVopDlOBPOswHNig_4,75232
|
563
|
+
sglang/srt/openai_api/protocol.py,sha256=1IVfYt0LUNLqFz0DNZyqxU02IRYVHcL7jnpMG9bNq34,13532
|
558
564
|
sglang/srt/platforms/interface.py,sha256=hym3iooBB4C8if5hDZezgVN6h4NIOu7sg2ZUBIV6XmM,11246
|
559
565
|
sglang/srt/sampling/custom_logit_processor.py,sha256=tDvoLgLqn-sy1qcY6vSrpbnHCeqbdk0uhMOO-uy4p4E,1099
|
560
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
566
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=4LCowU2bk0TOSfIGpEy90N1SpTsiOKK8Rx1ZYcklUFQ,11988
|
561
567
|
sglang/srt/sampling/sampling_params.py,sha256=nXm44Inn91YtrMpAm5mDb6-97owRy-Bh6lZ0BIpw73I,5919
|
562
568
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
563
569
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
564
570
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
565
571
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
566
572
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
567
|
-
sglang/srt/speculative/build_eagle_tree.py,sha256=
|
573
|
+
sglang/srt/speculative/build_eagle_tree.py,sha256=lt4sXUehPi26MT2-2Z0VivtF6AP7kirSaEO_u-YJ4J4,11670
|
568
574
|
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=FP-Dc6K4zaL2KQA8QsNccBM8TXnwREh1I2iPL9KHo8I,9252
|
569
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
570
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
575
|
+
sglang/srt/speculative/eagle_utils.py,sha256=iJYhklXHfDgEKbVB39HkVEea-XTEC60Z_LjIVjkrZQs,28701
|
576
|
+
sglang/srt/speculative/eagle_worker.py,sha256=D4G8hnwtc8xQt1okG4TY9wYSXbKTqGVDAD22AUXW6pA,26824
|
571
577
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
572
578
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
573
579
|
sglang/test/few_shot_gsm8k.py,sha256=7VLbWl4nCQs1wjtW4q-46jf9jUCycSs5Iw8v7sUSzBw,4284
|
574
580
|
sglang/test/few_shot_gsm8k_engine.py,sha256=QQbrwOX6-cJDD3RZC_e7zPnt6aSo8JdF8X_lRHSjdDM,3886
|
575
581
|
sglang/test/run_eval.py,sha256=9yO0hXZOcn4abEOs96T-XPguDEklK16Ltco0pGF3zCg,4020
|
576
|
-
sglang/test/runners.py,sha256=
|
582
|
+
sglang/test/runners.py,sha256=I2gXi0r663tvGlHLvh-W963Nv2yieA8MWVgwWe9zDbc,30656
|
577
583
|
sglang/test/send_one.py,sha256=6FhbJ3c8RpXxvFTELRXaF97GpT7zXXsCDYZh1DqG22E,2550
|
578
584
|
sglang/test/simple_eval_common.py,sha256=joqrGysuLnJFtzDRIgFkMsRyKUSyjVPFWp0_PHAL3Ik,12378
|
579
585
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
@@ -582,19 +588,19 @@ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWU
|
|
582
588
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
583
589
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
584
590
|
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
585
|
-
sglang/test/test_block_fp8.py,sha256=
|
591
|
+
sglang/test/test_block_fp8.py,sha256=3gOC4Xkxh2LXfT7T2aL8acWzpSdJlRdA3KlO0I1Wtkc,21594
|
586
592
|
sglang/test/test_block_fp8_ep.py,sha256=N1rvqbPErBaFFpeAw8TLYXGNZOoG7cfIBP2p5XbSyMo,10806
|
587
|
-
sglang/test/test_custom_ops.py,sha256=
|
593
|
+
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
588
594
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
589
595
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
590
596
|
sglang/test/test_programs.py,sha256=VZ3vXtUDBnXz0M7gFdDH8hXg9Wa0j_qI8CVqjEgRN_E,18877
|
591
|
-
sglang/test/test_utils.py,sha256=
|
597
|
+
sglang/test/test_utils.py,sha256=xk_o4zEDSNSy88Jiy7RA1fNfnBlYL-V49EzrLlf9bvM,30643
|
592
598
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
593
599
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
594
600
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
595
601
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=er0i3KGHMkw-4UZB1GCFd4oYwRcXfU5wpO1ORqpNGGA,7626
|
596
|
-
sglang-0.4.5.
|
597
|
-
sglang-0.4.5.
|
598
|
-
sglang-0.4.5.
|
599
|
-
sglang-0.4.5.
|
600
|
-
sglang-0.4.5.
|
602
|
+
sglang-0.4.5.post3.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
603
|
+
sglang-0.4.5.post3.dist-info/METADATA,sha256=aRgCmz8aysjesjP6QgqwsO3k3oLNVOonYv2-pl7GAE4,25592
|
604
|
+
sglang-0.4.5.post3.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
|
605
|
+
sglang-0.4.5.post3.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
606
|
+
sglang-0.4.5.post3.dist-info/RECORD,,
|
sglang/lang/__init__.py
DELETED
File without changes
|
@@ -1,25 +0,0 @@
|
|
1
|
-
from sglang.srt.lora.backend.base_backend import BaseLoRABackend
|
2
|
-
|
3
|
-
|
4
|
-
def get_backend_from_name(name: str) -> BaseLoRABackend:
|
5
|
-
"""
|
6
|
-
Get corresponding backend class from backend's name
|
7
|
-
"""
|
8
|
-
if name == "triton":
|
9
|
-
from sglang.srt.lora.backend.triton_backend import TritonLoRABackend
|
10
|
-
|
11
|
-
return TritonLoRABackend
|
12
|
-
elif name == "flashinfer":
|
13
|
-
from sglang.srt.lora.backend.flashinfer_backend import FlashInferLoRABackend
|
14
|
-
|
15
|
-
return FlashInferLoRABackend
|
16
|
-
else:
|
17
|
-
raise ValueError(f"Invalid backend: {name}")
|
18
|
-
|
19
|
-
|
20
|
-
__all__ = [
|
21
|
-
"BaseLoRABackend",
|
22
|
-
"FlashInferLoRABackend",
|
23
|
-
"TritonLoRABackend",
|
24
|
-
"get_backend_from_name",
|
25
|
-
]
|
sglang/srt/server.py
DELETED
@@ -1,18 +0,0 @@
|
|
1
|
-
# Copyright 2023-2024 SGLang Team
|
2
|
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
3
|
-
# you may not use this file except in compliance with the License.
|
4
|
-
# You may obtain a copy of the License at
|
5
|
-
#
|
6
|
-
# http://www.apache.org/licenses/LICENSE-2.0
|
7
|
-
#
|
8
|
-
# Unless required by applicable law or agreed to in writing, software
|
9
|
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
10
|
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
11
|
-
# See the License for the specific language governing permissions and
|
12
|
-
# limitations under the License.
|
13
|
-
# ==============================================================================
|
14
|
-
|
15
|
-
# Some shortcuts for backward compatibility.
|
16
|
-
# They will be removed in new versions.
|
17
|
-
from sglang.srt.entrypoints.engine import Engine
|
18
|
-
from sglang.srt.entrypoints.http_server import kill_process_tree, launch_server
|
File without changes
|
File without changes
|