sglang 0.4.6.post2__py3-none-any.whl → 0.4.6.post4__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sglang/bench_offline_throughput.py +4 -2
- sglang/bench_one_batch.py +3 -13
- sglang/bench_one_batch_server.py +143 -15
- sglang/bench_serving.py +158 -8
- sglang/compile_deep_gemm.py +1 -1
- sglang/eval/loogle_eval.py +157 -0
- sglang/lang/chat_template.py +119 -75
- sglang/lang/tracer.py +1 -1
- sglang/srt/code_completion_parser.py +1 -1
- sglang/srt/configs/deepseekvl2.py +5 -2
- sglang/srt/configs/device_config.py +1 -1
- sglang/srt/configs/internvl.py +696 -0
- sglang/srt/configs/janus_pro.py +3 -0
- sglang/srt/configs/model_config.py +18 -0
- sglang/srt/constrained/base_grammar_backend.py +55 -72
- sglang/srt/constrained/llguidance_backend.py +25 -21
- sglang/srt/constrained/outlines_backend.py +27 -26
- sglang/srt/constrained/reasoner_grammar_backend.py +22 -33
- sglang/srt/constrained/xgrammar_backend.py +71 -53
- sglang/srt/conversation.py +78 -46
- sglang/srt/disaggregation/base/conn.py +1 -0
- sglang/srt/disaggregation/decode.py +11 -3
- sglang/srt/disaggregation/fake/conn.py +1 -1
- sglang/srt/disaggregation/mini_lb.py +74 -23
- sglang/srt/disaggregation/mooncake/conn.py +236 -138
- sglang/srt/disaggregation/nixl/conn.py +242 -71
- sglang/srt/disaggregation/prefill.py +7 -4
- sglang/srt/disaggregation/utils.py +51 -2
- sglang/srt/distributed/device_communicators/custom_all_reduce.py +1 -8
- sglang/srt/distributed/device_communicators/npu_communicator.py +39 -0
- sglang/srt/distributed/device_communicators/pynccl.py +2 -1
- sglang/srt/distributed/device_communicators/shm_broadcast.py +2 -1
- sglang/srt/distributed/parallel_state.py +22 -1
- sglang/srt/entrypoints/engine.py +31 -4
- sglang/srt/entrypoints/http_server.py +45 -3
- sglang/srt/entrypoints/verl_engine.py +3 -2
- sglang/srt/function_call_parser.py +2 -2
- sglang/srt/hf_transformers_utils.py +20 -1
- sglang/srt/layers/attention/flashattention_backend.py +147 -51
- sglang/srt/layers/attention/flashinfer_backend.py +23 -13
- sglang/srt/layers/attention/flashinfer_mla_backend.py +62 -15
- sglang/srt/layers/attention/merge_state.py +46 -0
- sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py +1 -1
- sglang/srt/layers/attention/triton_ops/merge_state.py +96 -0
- sglang/srt/layers/attention/utils.py +4 -2
- sglang/srt/layers/attention/vision.py +290 -163
- sglang/srt/layers/dp_attention.py +71 -21
- sglang/srt/layers/layernorm.py +1 -1
- sglang/srt/layers/logits_processor.py +46 -11
- sglang/srt/layers/moe/ep_moe/kernels.py +343 -8
- sglang/srt/layers/moe/ep_moe/layer.py +121 -2
- sglang/srt/layers/moe/ep_moe/token_dispatcher.py +97 -54
- sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +5 -2
- sglang/srt/layers/moe/topk.py +1 -1
- sglang/srt/layers/quantization/__init__.py +1 -1
- sglang/srt/layers/quantization/blockwise_int8.py +2 -2
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +2 -4
- sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +2 -1
- sglang/srt/layers/quantization/deep_gemm.py +77 -71
- sglang/srt/layers/quantization/fp8.py +110 -97
- sglang/srt/layers/quantization/fp8_kernel.py +81 -62
- sglang/srt/layers/quantization/fp8_utils.py +71 -23
- sglang/srt/layers/quantization/int8_kernel.py +2 -2
- sglang/srt/layers/quantization/kv_cache.py +3 -10
- sglang/srt/layers/quantization/utils.py +0 -5
- sglang/srt/layers/quantization/w8a8_fp8.py +8 -10
- sglang/srt/layers/sampler.py +0 -4
- sglang/srt/layers/vocab_parallel_embedding.py +18 -7
- sglang/srt/lora/lora_manager.py +11 -14
- sglang/srt/lora/mem_pool.py +4 -4
- sglang/srt/lora/triton_ops/gate_up_lora_b.py +1 -1
- sglang/srt/lora/triton_ops/qkv_lora_b.py +1 -1
- sglang/srt/lora/triton_ops/sgemm_lora_a.py +1 -1
- sglang/srt/lora/triton_ops/sgemm_lora_b.py +1 -1
- sglang/srt/lora/utils.py +1 -1
- sglang/srt/managers/cache_controller.py +115 -119
- sglang/srt/managers/data_parallel_controller.py +3 -3
- sglang/srt/managers/detokenizer_manager.py +21 -8
- sglang/srt/managers/io_struct.py +13 -1
- sglang/srt/managers/mm_utils.py +1 -1
- sglang/srt/managers/multimodal_processors/base_processor.py +5 -0
- sglang/srt/managers/multimodal_processors/internvl.py +232 -0
- sglang/srt/managers/multimodal_processors/llava.py +46 -0
- sglang/srt/managers/multimodal_processors/pixtral.py +127 -0
- sglang/srt/managers/schedule_batch.py +93 -23
- sglang/srt/managers/schedule_policy.py +11 -8
- sglang/srt/managers/scheduler.py +140 -100
- sglang/srt/managers/scheduler_output_processor_mixin.py +124 -55
- sglang/srt/managers/tokenizer_manager.py +157 -47
- sglang/srt/managers/tp_worker.py +21 -21
- sglang/srt/managers/tp_worker_overlap_thread.py +22 -11
- sglang/srt/mem_cache/chunk_cache.py +2 -0
- sglang/srt/mem_cache/memory_pool.py +4 -2
- sglang/srt/metrics/collector.py +312 -37
- sglang/srt/model_executor/cuda_graph_runner.py +10 -11
- sglang/srt/model_executor/forward_batch_info.py +1 -1
- sglang/srt/model_executor/model_runner.py +57 -41
- sglang/srt/model_loader/loader.py +18 -11
- sglang/srt/models/clip.py +4 -4
- sglang/srt/models/deepseek_janus_pro.py +3 -3
- sglang/srt/models/deepseek_nextn.py +1 -20
- sglang/srt/models/deepseek_v2.py +77 -39
- sglang/srt/models/gemma3_mm.py +1 -1
- sglang/srt/models/internlm2.py +3 -0
- sglang/srt/models/internvl.py +670 -0
- sglang/srt/models/llama.py +3 -1
- sglang/srt/models/llama4.py +58 -13
- sglang/srt/models/llava.py +248 -5
- sglang/srt/models/minicpmv.py +1 -1
- sglang/srt/models/mixtral.py +98 -34
- sglang/srt/models/mllama.py +1 -1
- sglang/srt/models/phi3_small.py +16 -2
- sglang/srt/models/pixtral.py +467 -0
- sglang/srt/models/qwen2_5_vl.py +8 -4
- sglang/srt/models/qwen2_vl.py +4 -4
- sglang/srt/models/roberta.py +1 -1
- sglang/srt/models/torch_native_llama.py +1 -1
- sglang/srt/models/xiaomi_mimo.py +171 -0
- sglang/srt/openai_api/adapter.py +52 -42
- sglang/srt/openai_api/protocol.py +20 -16
- sglang/srt/reasoning_parser.py +1 -1
- sglang/srt/sampling/custom_logit_processor.py +18 -3
- sglang/srt/sampling/sampling_batch_info.py +2 -2
- sglang/srt/sampling/sampling_params.py +2 -0
- sglang/srt/server_args.py +64 -10
- sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +3 -3
- sglang/srt/speculative/eagle_utils.py +7 -7
- sglang/srt/speculative/eagle_worker.py +22 -19
- sglang/srt/utils.py +41 -6
- sglang/test/few_shot_gsm8k.py +2 -2
- sglang/test/few_shot_gsm8k_engine.py +2 -2
- sglang/test/run_eval.py +2 -2
- sglang/test/runners.py +8 -1
- sglang/test/send_one.py +13 -3
- sglang/test/simple_eval_common.py +1 -1
- sglang/test/simple_eval_humaneval.py +1 -1
- sglang/test/test_block_fp8.py +2 -2
- sglang/test/test_deepep_utils.py +219 -0
- sglang/test/test_programs.py +5 -5
- sglang/test/test_utils.py +92 -15
- sglang/utils.py +1 -1
- sglang/version.py +1 -1
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post4.dist-info}/METADATA +18 -9
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post4.dist-info}/RECORD +150 -137
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post4.dist-info}/WHEEL +1 -1
- /sglang/{llama3_eval.py → eval/llama3_eval.py} +0 -0
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post4.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.6.post2.dist-info → sglang-0.4.6.post4.dist-info}/top_level.txt +0 -0
@@ -1,22 +1,23 @@
|
|
1
1
|
sglang/__init__.py,sha256=T-fZEjKP66Q1q3PB56oREs5U3zf6bL0fNcdIbW8jMhE,1652
|
2
2
|
sglang/api.py,sha256=vHiKBg8wwIdmrpnGclop5BzJ-1Q88emrlrfLwNCHg98,7010
|
3
|
-
sglang/bench_offline_throughput.py,sha256=
|
4
|
-
sglang/bench_one_batch.py,sha256=
|
5
|
-
sglang/bench_one_batch_server.py,sha256=
|
6
|
-
sglang/bench_serving.py,sha256=
|
3
|
+
sglang/bench_offline_throughput.py,sha256=G1lLm5F-ZE9HCb7tBi7GqhlZaDelgG4or4HgUSAD0sE,13877
|
4
|
+
sglang/bench_one_batch.py,sha256=4XysFhY3fbJmVXVaIAvwb0dx5TYTtO8ONAAzTFT-ixQ,19222
|
5
|
+
sglang/bench_one_batch_server.py,sha256=XJNBXYEuhU3vuSXJ2BRDAwlSPUmnC-gLCCJ1FSpuC9A,10894
|
6
|
+
sglang/bench_serving.py,sha256=JkPLvFxCax5EKw-0DSoGxuFte2loApCIW7fGI_MuWsI,62931
|
7
7
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
8
|
-
sglang/compile_deep_gemm.py,sha256=
|
8
|
+
sglang/compile_deep_gemm.py,sha256=XaKt2M4BMSiV8gx3ERzX5YwwEoE7suvUqgoi_wYlNpQ,6211
|
9
9
|
sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
10
10
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
11
|
-
sglang/
|
12
|
-
sglang/
|
13
|
-
sglang/
|
14
|
-
sglang/
|
11
|
+
sglang/utils.py,sha256=6Zpzw96ZDrZcBAI-OFmWtKvXcLBVLiHok0B42pK3kKs,16160
|
12
|
+
sglang/version.py,sha256=Rr2NlJlI5ama66BpRjzDUs7DOzgB59i8o_MYW0YO2X8,28
|
13
|
+
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
14
|
+
sglang/eval/loogle_eval.py,sha256=pRPVA4fxGmT3_oXvXnlNE-UlPrcQGLBJF-OSE9YWJXM,4336
|
15
|
+
sglang/lang/chat_template.py,sha256=HKlx7snSWFED8GKF5ex79sQrPWFw5TSXQM0_LsiD9Bc,20552
|
15
16
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
16
17
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
17
18
|
sglang/lang/interpreter.py,sha256=OH1SFCm4rUCPO32MTo8j5V2Z13Jic7_r1GQOP1-aHaw,33234
|
18
19
|
sglang/lang/ir.py,sha256=gssBGxqQEVJmjR_PqG2yah48AsInGaO3CmnQ2boJThc,18769
|
19
|
-
sglang/lang/tracer.py,sha256=
|
20
|
+
sglang/lang/tracer.py,sha256=ljBo9VZ0zVaGwzNk32qw21acyo60N0UjIjqBbT5a1WI,8175
|
20
21
|
sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
21
22
|
sglang/lang/backend/anthropic.py,sha256=qXWqqFlk0-nC62QCcYIRjLTc4AHrdTKpl7hCeDzROUs,2019
|
22
23
|
sglang/lang/backend/base_backend.py,sha256=tEutGCU5tni1xGlrIjAVvA9aflJBt2duKrIDzqabJWc,1975
|
@@ -26,30 +27,31 @@ sglang/lang/backend/runtime_endpoint.py,sha256=4pTG1TnOVTWBCh3rMhqL_NP2hsawG9xuP
|
|
26
27
|
sglang/lang/backend/vertexai.py,sha256=gz0uNYyBb88jbPYz6ZIJ774fefrcbuVdoK33bphUZpI,4827
|
27
28
|
sglang/srt/_custom_ops.py,sha256=L7NuEaRD_Q6Q54n0NZnLXgWZURbnn8Tkg4NQedE6zgA,3616
|
28
29
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
29
|
-
sglang/srt/code_completion_parser.py,sha256=
|
30
|
-
sglang/srt/conversation.py,sha256=
|
30
|
+
sglang/srt/code_completion_parser.py,sha256=vafJqdTTreD9kvCsoMuxP_fFmoue7pOA1ibI9KXg4mE,5405
|
31
|
+
sglang/srt/conversation.py,sha256=569K5QEjnZGF45GjFGVZfP1n8RqmpcwxuVbgWRNFyis,35295
|
31
32
|
sglang/srt/custom_op.py,sha256=J1PUcGaeJJjfAjp06BQsLpUkKyR1zsh9MvDiDlqqJsg,1129
|
32
|
-
sglang/srt/function_call_parser.py,sha256=
|
33
|
-
sglang/srt/hf_transformers_utils.py,sha256=
|
33
|
+
sglang/srt/function_call_parser.py,sha256=W3ZBbYP1Eg5z70sc1-HVhT_b1TJg5oxZDuGOppgMrA8,33378
|
34
|
+
sglang/srt/hf_transformers_utils.py,sha256=97J396flSaelvOIn0zO8Ji3bvFWUiL2mhLgxnup-d-M,10054
|
34
35
|
sglang/srt/mm_utils.py,sha256=1ScBunw_x4W8ebM_AcJ62-1T2mfT8NlMJqdAhkF1lb0,12367
|
35
36
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
36
37
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
37
|
-
sglang/srt/reasoning_parser.py,sha256=
|
38
|
-
sglang/srt/server_args.py,sha256=
|
38
|
+
sglang/srt/reasoning_parser.py,sha256=lZN5b1TJp3EK2GzxcICQhp0tRQjQw3ROOrjRgQe6Bsc,6341
|
39
|
+
sglang/srt/server_args.py,sha256=gW3mDnnRqrtpZTZOmjeWPfdnDNr070tSpUMrl7Qlc_Y,59525
|
39
40
|
sglang/srt/torch_memory_saver_adapter.py,sha256=HYlgYJ2sgmjs2RSjU2KbCaXijRg3mTDZ0ZcCB5Bt6Ps,2211
|
40
|
-
sglang/srt/utils.py,sha256=
|
41
|
+
sglang/srt/utils.py,sha256=8xEOCR2aw4InlcwrdIN9EFfR-1FU26T_VylU5FQJ4-s,66467
|
41
42
|
sglang/srt/warmup.py,sha256=FmJiYfjRr3X_eAe7ojQaPoN17LvHpjDmRWRnO-k86AQ,1469
|
42
43
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
43
44
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
44
45
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
45
|
-
sglang/srt/configs/deepseekvl2.py,sha256=
|
46
|
-
sglang/srt/configs/device_config.py,sha256=
|
46
|
+
sglang/srt/configs/deepseekvl2.py,sha256=X8Q2gm7og_Ylx6tbFXetusfIJIXjWY_YH_p90C67BTI,23397
|
47
|
+
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
47
48
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
48
|
-
sglang/srt/configs/
|
49
|
+
sglang/srt/configs/internvl.py,sha256=0wUu_ExziVaA6bJjJ6VKP1uFJOHlj6fVx6y5wLSqJvw,27722
|
50
|
+
sglang/srt/configs/janus_pro.py,sha256=Rrb7kQsNaUP-TiZrjNk8Lr1momFrql8ScEunnrH0_xM,19086
|
49
51
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
50
52
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
51
53
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
52
|
-
sglang/srt/configs/model_config.py,sha256=
|
54
|
+
sglang/srt/configs/model_config.py,sha256=MONwgieC5BZ2fPq31a-xTTx-RzPu1OGUBaEkcpdFkjU,23896
|
53
55
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
54
56
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
55
57
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -59,82 +61,85 @@ sglang/srt/connector/utils.py,sha256=isTvxauz1_8no5MW6p8Bwj2H9mQkweaRO_RSwAPA7R8
|
|
59
61
|
sglang/srt/connector/serde/__init__.py,sha256=MvBJ7FBJtnou-AD-EdsCdAIDCcA8kWvUNuRViILVJ-0,718
|
60
62
|
sglang/srt/connector/serde/safe_serde.py,sha256=Iv_mFsDvk-cXuw0WTykBZ2yGxW0jb82DwVqC7r3RmAU,750
|
61
63
|
sglang/srt/connector/serde/serde.py,sha256=n59I2MXLa7WCyN_8pEd8L-scJk7lMhmEX-GOUIhF0ZA,1004
|
62
|
-
sglang/srt/constrained/base_grammar_backend.py,sha256=
|
63
|
-
sglang/srt/constrained/llguidance_backend.py,sha256=
|
64
|
-
sglang/srt/constrained/outlines_backend.py,sha256=
|
64
|
+
sglang/srt/constrained/base_grammar_backend.py,sha256=c7EbA6o_OlZTeUPkTcMVR0lNkZiCUo8C7ra5z7DJork,6822
|
65
|
+
sglang/srt/constrained/llguidance_backend.py,sha256=FP_Mafzb034Q62v19NZsdDQQ2iSl-dfLvCFuB8BsFFA,6117
|
66
|
+
sglang/srt/constrained/outlines_backend.py,sha256=P0EE0OoaJmxas0hnPN8Xz9vtST0J8f-wzuTsDY0aA2w,6864
|
65
67
|
sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCXIRfr8k_ZDviJyte048,6824
|
66
|
-
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=
|
67
|
-
sglang/srt/constrained/xgrammar_backend.py,sha256=
|
68
|
+
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
69
|
+
sglang/srt/constrained/xgrammar_backend.py,sha256=FKWrMb1QSgtCTCyk6pQZ5NS-5T3M6dvdxN7OOPCYc8A,7837
|
68
70
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
69
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
70
|
-
sglang/srt/disaggregation/mini_lb.py,sha256=
|
71
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
72
|
-
sglang/srt/disaggregation/utils.py,sha256=
|
71
|
+
sglang/srt/disaggregation/decode.py,sha256=WDaXASJn2cp35r6ySPDdm5oXXg-3kR714CXX5xG28fY,25378
|
72
|
+
sglang/srt/disaggregation/mini_lb.py,sha256=SROT_-_OdZSD3R7ar2g90vL5WX5Ijc-K99zz7ewWD7w,12389
|
73
|
+
sglang/srt/disaggregation/prefill.py,sha256=Sf8wRv7BDBv0QQTahXR5wMTCiqOddhymx7L7vQbswXE,15527
|
74
|
+
sglang/srt/disaggregation/utils.py,sha256=W3Fe_MwJrSxHC1eMZRkD7C09VWFKRwfoM9_XXY-n2s0,5054
|
73
75
|
sglang/srt/disaggregation/base/__init__.py,sha256=KR8xXoRCDAy2U623mfP6ujXu42m1_F9EiudjrKu2I_A,130
|
74
|
-
sglang/srt/disaggregation/base/conn.py,sha256=
|
76
|
+
sglang/srt/disaggregation/base/conn.py,sha256=hEOuR6kXrc7fRSYE9RAH53DLGHGaCcYWod6IkmtNttg,2491
|
75
77
|
sglang/srt/disaggregation/fake/__init__.py,sha256=zmfeKYXjonRhfFOck1c_mP7Q4cW5G0f1RsTwRivKu0s,47
|
76
|
-
sglang/srt/disaggregation/fake/conn.py,sha256=
|
78
|
+
sglang/srt/disaggregation/fake/conn.py,sha256=N9y0ZBhfPkrhaKN3gsRxqb2wWpiioaANtFqO9wVl2Ec,2553
|
77
79
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=1vacEHmWjf7zgbMPzsXKB08FqNKNCquJdUiDlO41BOk,122
|
78
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
80
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=MF2N1FbBdI5mh5Btl6gkX6Dw8MqjKPMVe9NvwdspEdY,33652
|
79
81
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=MxDAB9ZetRF1pFS2LP3FVHPtQ1HjIt_SK3UMaYHZ94o,2604
|
80
82
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=n9HjrRk36WUcZNeetGWOh2pSriLp7GNTq7YYX9K3EtY,85
|
81
|
-
sglang/srt/disaggregation/nixl/conn.py,sha256=
|
83
|
+
sglang/srt/disaggregation/nixl/conn.py,sha256=ekYUmS2c9TnkFrzS1DYGXZG-Yrb5WbMIL6gnQHAxG8M,30104
|
82
84
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
83
85
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
84
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
86
|
+
sglang/srt/distributed/parallel_state.py,sha256=cCQq94H8A-rO2wZf_bCf1lkwcTVOBrHubM9K1PrzVSY,51560
|
85
87
|
sglang/srt/distributed/utils.py,sha256=U-BSaXYjWwnfG8g-tUfBhjKt5Ug097nyHtu3g3aea_Y,8473
|
86
88
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
87
|
-
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=
|
89
|
+
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=qje-PQ3v8yaV-oYVLPws1mgIlXVsGKFCOvXHmSe8ZXg,19624
|
88
90
|
sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py,sha256=fLoptT_U0lVAqkhEg-ge53CdFSIKQpDRiqHYKwJVEZg,10974
|
89
91
|
sglang/srt/distributed/device_communicators/hpu_communicator.py,sha256=gPjEH1-izoby5uDrfUlzNf21luPT0Ow7pJjhCRKnHy8,1728
|
90
|
-
sglang/srt/distributed/device_communicators/
|
92
|
+
sglang/srt/distributed/device_communicators/npu_communicator.py,sha256=bRXN1Md_4SHQGzQYZa2GrHv2zbIU5vSpkueHiAZL1xQ,1345
|
93
|
+
sglang/srt/distributed/device_communicators/pynccl.py,sha256=obXyCaZznZHSt486XCnEOBNG3Cen7ysuuMuGRlTTl-8,10095
|
91
94
|
sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6EMz-oPS9J16WHo2Q_SRL1DtlJKK63Hfg,15349
|
92
|
-
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=
|
95
|
+
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
93
96
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
94
97
|
sglang/srt/entrypoints/EngineBase.py,sha256=xoyvp6XAeDLY2_Q2Ng33H-fRhrXHv2ldJJKd-HuDhqE,1870
|
95
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
96
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
98
|
+
sglang/srt/entrypoints/engine.py,sha256=0L0jis9GLehFgkYP9cBBw7-Plg7e_quCF5OiX82O8io,24704
|
99
|
+
sglang/srt/entrypoints/http_server.py,sha256=xH-iXPx9wg2VqHW9dFxDAyIwcdBMAsUboK7MH4SR-5E,31003
|
97
100
|
sglang/srt/entrypoints/http_server_engine.py,sha256=ihA6y3GXRs28Y9U3SgdQcJQjnw_SVIby7QrVgiafX04,4846
|
98
|
-
sglang/srt/entrypoints/verl_engine.py,sha256=
|
101
|
+
sglang/srt/entrypoints/verl_engine.py,sha256=RYizNetTHzcB8dErX1EW4NsyRNGkFPljYaAf7pVRPdM,7002
|
99
102
|
sglang/srt/layers/activation.py,sha256=oSkdo8B8najXFcVay3Y__CEvgXh87lAIhG0CMp2Ugqs,5954
|
100
|
-
sglang/srt/layers/dp_attention.py,sha256=
|
103
|
+
sglang/srt/layers/dp_attention.py,sha256=MwqjY3uOg4dKjFxTyNlWnnHaA0oLL3oUkapfh0qs1IE,9438
|
101
104
|
sglang/srt/layers/elementwise.py,sha256=XCrR2i-9dP-H6jQo2zUuquwZrsl_wEQqj5Wxk6WUf7o,13987
|
102
|
-
sglang/srt/layers/layernorm.py,sha256=
|
105
|
+
sglang/srt/layers/layernorm.py,sha256=kU47PX_V46RblaxxMNxWxGjWSa99o0w2s68908rGp6Q,5957
|
103
106
|
sglang/srt/layers/linear.py,sha256=nC9MxJrFap1BEyqgFlBySH4IeQruIbcBp32cOhUl5Fw,52149
|
104
|
-
sglang/srt/layers/logits_processor.py,sha256=
|
107
|
+
sglang/srt/layers/logits_processor.py,sha256=eeG2zXZguvz2r1OVKVd5HFSPseL5fzRenh0cYuKO-GQ,25557
|
105
108
|
sglang/srt/layers/parameter.py,sha256=zqWyEzpWzP4NNTjq3G9khq6XofgpcmJqQLg6Vd4WyWE,15084
|
106
109
|
sglang/srt/layers/pooler.py,sha256=nR9F4x0GP2KYkJihhcL-TX30gfLY3mVhOLRfeBDeKL4,1942
|
107
110
|
sglang/srt/layers/radix_attention.py,sha256=F71GgDes_fEt_cHxR9HM2QhNG5u7uF4zDAuLqwLYEV4,3481
|
108
111
|
sglang/srt/layers/rotary_embedding.py,sha256=eVBwYvGpFhL1KyyPutQuZotmvSpChcxzyhpmcbQ6cKQ,48267
|
109
|
-
sglang/srt/layers/sampler.py,sha256=
|
112
|
+
sglang/srt/layers/sampler.py,sha256=JmzceFPgl3vjaf9VQA3OPEW52tRZ_njrOxpGdZ35LP0,11261
|
110
113
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
111
114
|
sglang/srt/layers/utils.py,sha256=tkTz86DFZ4NRMEUc4QkYNskUskdxXoEqkWqaMGbhP7E,1045
|
112
|
-
sglang/srt/layers/vocab_parallel_embedding.py,sha256=
|
115
|
+
sglang/srt/layers/vocab_parallel_embedding.py,sha256=GPKCQiR2yH5Z2XSE9g3vWObdegcwPnMHXv7qEZovLH4,22755
|
113
116
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=lGujcYJ_CxHJy0Q9L6Phn3ds-nBGMy0OGj3R54R65iQ,3334
|
114
117
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=kCNn5Ub0jCsFjhVhuE-9qK53gu5a9oMStMeT2lcc6CU,9904
|
115
118
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
116
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
117
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
118
|
-
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=
|
119
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=o9ggOpIAhmLzxRfVg8mjLM_x6vesOb5f6MayVZe0UJU,87868
|
120
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=53TXhmBpU5rs04-4u-yXclwJ5UYg7WJfyLDZJ8nSDOU,47651
|
121
|
+
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=4BJy18GHYiNVjcSkvmzxgoSk8nugsLrZuars_m-4oYw,32406
|
119
122
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=wR0bkLz3mj5EfuHEi9fwEP2vtq6xFhsrIijpFb009o4,10340
|
123
|
+
sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZwR4_XiLOIvbrk,1423
|
120
124
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=K5hUqBgakk2COSQqsaxWs0yEVOHS-7BlOygZTOeI8kE,9444
|
121
125
|
sglang/srt/layers/attention/triton_backend.py,sha256=oEEiUwHbm4rNw5ExbQ2c3n0TwAgkk77yuLFenj9bHOo,26902
|
122
|
-
sglang/srt/layers/attention/utils.py,sha256=
|
123
|
-
sglang/srt/layers/attention/vision.py,sha256=
|
126
|
+
sglang/srt/layers/attention/utils.py,sha256=3NyDQ2T2IHwFb5mAJzbpyxRYmdkB8htM3_9_U5GqQDY,2889
|
127
|
+
sglang/srt/layers/attention/vision.py,sha256=TOTRWzd5d_9fCR8DOvy_oY-vJ1zl2cVYni5hlZGDens,15355
|
124
128
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=DPu_aCPgwPqKWZPEQmp_xA7MPbpV2ip-MEICCB470Ao,19120
|
125
|
-
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=
|
129
|
+
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
126
130
|
sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=m12jEnQkNJguATqvZ57HtMC2hhU4wqdB8xAYdh25BxE,13922
|
131
|
+
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
127
132
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
128
133
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
129
134
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=U0qh3udHuJJll3udydqABoXPFz0au9aEj8Lv7OAHYvQ,4655
|
130
135
|
sglang/srt/layers/moe/router.py,sha256=5Aeqoix_AS4uymb665OJE904wVSBkQeFdZP4e7KKPvg,10530
|
131
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
136
|
+
sglang/srt/layers/moe/topk.py,sha256=ir3CXINtE2xeLJDh9S3PlxikRC0e4AIxb-lEQqttnBk,11127
|
132
137
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
133
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
134
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
135
|
-
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=
|
138
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=tj2yIWdgn3zaz9uuhsm6qx4syaX_t-zpYPLKotCX89k,33547
|
139
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=TPBcD9_To_sQhayur9nbQNRn8AYTCO3gXtytKHfUkGM,40349
|
140
|
+
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=y-t3qG0GS9r8GLTe6_-5BV43Sp5BPHIoveDlYFGIt7s,22051
|
136
141
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=h9yMFAL_bagUf-qBED8gSWdCOb7d8IdA-pE-L_nIg8E,842
|
137
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
142
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=mNFBkSB9n1axyLAs9dsIwdAj7L5w9ZFEEDsxOL6XPPE,55996
|
138
143
|
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BMOV76fabrZcoyDmRpRbH11Jc0ogWH2k2QAQwvZIpgI,25084
|
139
144
|
"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
|
140
145
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
@@ -208,9 +213,11 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BMOV76fabrZcoyDmRpRbH11Jc
|
|
208
213
|
"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
|
209
214
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json",sha256=Sc9xK1wtRUqIzXppbutcq-Y2e9M0DZl2OGVzzB0aQuI,3265
|
210
215
|
"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
|
216
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=8gNamin6OqMiQ-LMVe4yQBo9ONioiC4loSWPnKcS1XI,3262
|
211
217
|
"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
|
212
218
|
"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=P8GpVR8fjrX7OFbBBFE4y4MJ4uhgoyUV4NYCm1qhWxk,3266
|
213
219
|
"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
|
220
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=XyiOCufhAu5BCMHoW9q4gLSRQEGd22bJnJkw15MqFYg,3267
|
214
221
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=f5HTi_9fWvInEyJp8pFgaVN6A9vxu3_845eSZGN9Ypo,3264
|
215
222
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=Piw4LN6d8QYrUahWsw3XUOtTMD1o3vHPwA94sGI56Gk,3242
|
216
223
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=3T8_rF2PEojhgTMyQ8DscXgJCWWdWfDPj4M434zWcA4,3243
|
@@ -287,31 +294,31 @@ sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BMOV76fabrZcoyDmRpRbH11Jc
|
|
287
294
|
"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
|
288
295
|
"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
|
289
296
|
"sglang/srt/layers/moe/fused_moe_triton/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Uz5X80VcNBOaxshwVNUEittHk2zqB4HQCfTJ4TPG5aM,3274
|
290
|
-
sglang/srt/layers/quantization/__init__.py,sha256=
|
297
|
+
sglang/srt/layers/quantization/__init__.py,sha256=0qQgvF5wR9VlYO9xv8GERPgtKWZ9OMilaxcSUeGTyN8,12424
|
291
298
|
sglang/srt/layers/quantization/awq.py,sha256=KemDG55U3B6YZVjMV71awVAIj0islFvtxcUHmOBeGy0,6739
|
292
299
|
sglang/srt/layers/quantization/base_config.py,sha256=jWk_egQrVNMYmQgbTI9vkcgzScLFjB5_sywFlAfE5J0,4776
|
293
|
-
sglang/srt/layers/quantization/blockwise_int8.py,sha256=
|
294
|
-
sglang/srt/layers/quantization/deep_gemm.py,sha256=
|
295
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
296
|
-
sglang/srt/layers/quantization/fp8_kernel.py,sha256=
|
297
|
-
sglang/srt/layers/quantization/fp8_utils.py,sha256=
|
300
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=BgPrsTakDDFirALkW9q9VmFk0wFZv9cotkTU69Gnxeo,15122
|
301
|
+
sglang/srt/layers/quantization/deep_gemm.py,sha256=a8T2IdWV11m4tnXfSwEmNzb_LwdaXcuaseFRsR07TtM,13124
|
302
|
+
sglang/srt/layers/quantization/fp8.py,sha256=QguTeY-PMgU5Vu3QdeqmS3DgFD1R9avwgBZABG92dcg,40709
|
303
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=OKpebbn09CpRzxFgB-RB_I4ZnWGLJ9nR0YTFu6-ZMdw,32570
|
304
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=VHU7glWyKjAMvR-zXAvZIuqMk6V3fj-rOx9K3xR-LEE,20075
|
298
305
|
sglang/srt/layers/quantization/gptq.py,sha256=gyGMOPXHzozK7pPWSjKgLdFX9h7MCEww7n8FqEVEVac,15364
|
299
|
-
sglang/srt/layers/quantization/int8_kernel.py,sha256=
|
306
|
+
sglang/srt/layers/quantization/int8_kernel.py,sha256=W9sXTIs46LJQPHLCt6UjoAVkIZhUn5eWq8pbyQBHpSo,12163
|
300
307
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
301
|
-
sglang/srt/layers/quantization/kv_cache.py,sha256
|
308
|
+
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
302
309
|
sglang/srt/layers/quantization/modelopt_quant.py,sha256=TpPgtbV7O5r1JY4Wm0np2pReQO6XERIdEDQcV41oTn0,16596
|
303
310
|
sglang/srt/layers/quantization/moe_wna16.py,sha256=KtFr4lIslMA12yx4JjXXPOsa5OHjxXWA6scYCRQnFMQ,19483
|
304
|
-
sglang/srt/layers/quantization/utils.py,sha256=
|
305
|
-
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=
|
311
|
+
sglang/srt/layers/quantization/utils.py,sha256=AXvGD8KRZVVrkRR1Y64fGkz4lkUP-CAjAQdp0LDNXrE,5266
|
312
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=UFwlch8qEm2J4muM4hMATj06-rf-__lSbBqVr00j1tc,11459
|
306
313
|
sglang/srt/layers/quantization/w8a8_int8.py,sha256=MkvmcxQj3X5AZbx8pgnHYAikc_Xd_jOhJXaxx7255ho,8984
|
307
314
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
308
315
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=EaOKuIA0zXwqmH_eVhWeNdGJT9d1d9gVvFyYkgpdjDg,25665
|
309
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
316
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=cGckgXOZQGMv7VIVQeXYblvHKUFC8hLpQfwNb18rj7E,26191
|
310
317
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
311
318
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
312
319
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
313
320
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=-iq634sU38yWFA-h3w-B4kTALeXMo7uRZQI6CckMZTo,5494
|
314
|
-
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=
|
321
|
+
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=SkeQYXW5i6M3ZLp867KFwQXVBcIPAcdYFILUTY0A850,5934
|
315
322
|
"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
|
316
323
|
"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
|
317
324
|
"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
|
@@ -467,167 +474,173 @@ sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a
|
|
467
474
|
sglang/srt/lora/layers.py,sha256=xdP2Gwlw9PCPZBhujGqO6aBn0eGxpVeIBFUp1LIGCto,13119
|
468
475
|
sglang/srt/lora/lora.py,sha256=uNvbjZ_Wr1SLI9-ElRJA_JKwkibSGroP5Bfpsr9MI-Y,7527
|
469
476
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
470
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
471
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
472
|
-
sglang/srt/lora/utils.py,sha256=
|
477
|
+
sglang/srt/lora/lora_manager.py,sha256=1vkfpx5EfkGji08xUFEBTNfeDjpjfieQDRScIbEmO3w,11528
|
478
|
+
sglang/srt/lora/mem_pool.py,sha256=dIx_8yZiJkFMyddfKL9G0zzgDxdkCQjG2qrbdHxqPtA,9633
|
479
|
+
sglang/srt/lora/utils.py,sha256=S53SOjYqeEc9toqGaThod9MNWEJs0OJew6KY558cMF0,5250
|
473
480
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
474
481
|
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
475
482
|
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
476
483
|
sglang/srt/lora/triton_ops/__init__.py,sha256=JGOYPIn1XbGcyJTbt8A0qoc02PYONSGNNjGkC8yJpAM,283
|
477
|
-
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=
|
478
|
-
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=
|
479
|
-
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=
|
480
|
-
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=
|
481
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
484
|
+
sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=vOUDzC_Sq7UGnDbdF8F7ChKG12hDIOFwwMb7e62Lz9w,5280
|
485
|
+
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=qCpJAksCSXS3Znm-ABx1QfrdNqj9hrP61oaeW-n2RhU,5945
|
486
|
+
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=yNBgl8jS76DPlGJg8puRkSnKkewf2_2oKfVZZRq4lYY,4351
|
487
|
+
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=EoF9HymgQ1V9DwyOJOvbw1hCbEjprVOne_fC4VHgj-s,4518
|
488
|
+
sglang/srt/managers/cache_controller.py,sha256=RDKuRuRdrMWhsy4QOXvtTG_u_NQUQFly7a6BnoEYiMY,18434
|
482
489
|
sglang/srt/managers/configure_logging.py,sha256=fOJaXAQ1n9m-8KPJndpsKvS885i69SMafoEADLIVfIM,1633
|
483
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=
|
484
|
-
sglang/srt/managers/detokenizer_manager.py,sha256=
|
490
|
+
sglang/srt/managers/data_parallel_controller.py,sha256=nB4CD_g8VShTZHCQ9sfst73lQeSvOChFzeY-6RRAhL8,11648
|
491
|
+
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
485
492
|
sglang/srt/managers/expert_distribution.py,sha256=r3o5RGI0gnV7xb60AApqKYa0oiSB37oB7hQBX7P3xZM,3225
|
486
|
-
sglang/srt/managers/io_struct.py,sha256=
|
487
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
493
|
+
sglang/srt/managers/io_struct.py,sha256=A6Odr-nyO3CJ0925m_2zCnvra6oQAFPU2o7F9TqSD70,31835
|
494
|
+
sglang/srt/managers/mm_utils.py,sha256=qTxNjMWdQwPpWBjk86eOS-UEgkfwNq5WwYiREK3wRso,18090
|
488
495
|
sglang/srt/managers/multimodal_processor.py,sha256=XlRYvNhF6XOssreRX9DZPhLSpps_VE62gSKw3EGdNPo,2088
|
489
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
490
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
491
|
-
sglang/srt/managers/scheduler.py,sha256=
|
492
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=
|
496
|
+
sglang/srt/managers/schedule_batch.py,sha256=OhrWYd_ywWiNNMOp_fcDOIwYt9_gX7oZnR9imEXbkb4,67564
|
497
|
+
sglang/srt/managers/schedule_policy.py,sha256=mCgwmhCTpzQJawiNizIxjY4nszkxokMmMz9DlDGGUa8,19666
|
498
|
+
sglang/srt/managers/scheduler.py,sha256=2TzJU0DZ_nmLnYJjQGn_JZJdfG-cDQnuMZUrINiOwsU,91483
|
499
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=aaj0z1PD3fGIOPoTtWwqoKsii0yQCR7txVFXMPECveQ,29879
|
493
500
|
sglang/srt/managers/session_controller.py,sha256=o-ifit0n4_xHLNmyD0Ams8FxGRgxFybX-Vz1hwgr3UQ,5755
|
494
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
495
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
496
|
-
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=
|
501
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=DMGNicPMCudO81ryP4zPC9GbO6cAkouGNUHtSQ4f_pQ,56162
|
502
|
+
sglang/srt/managers/tp_worker.py,sha256=cnI2JRxDqM7RXaaXAnLHNyYH4Jt7SB6HLAD5fRoWoNA,10025
|
503
|
+
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=W-FP7dkR9_voS0emMj4N5ML3Iao9gNZc-on6iUflbrw,9835
|
497
504
|
sglang/srt/managers/utils.py,sha256=5i75uLlQOF_5CaT02CrWtwozMTtwTg2_nLP8Dtr-JZQ,1536
|
498
|
-
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=
|
505
|
+
sglang/srt/managers/multimodal_processors/base_processor.py,sha256=DMeqUdxyOZ5IKo-Z2NjEteJS-Oz6gG9jyU27c8QwA5A,10367
|
499
506
|
sglang/srt/managers/multimodal_processors/clip.py,sha256=lRc2mcuDbAhZVf-0EfkO81pqDiol9zLvTpDqtPIBQ2k,1525
|
500
507
|
sglang/srt/managers/multimodal_processors/deepseek_vl_v2.py,sha256=hpjpGFzlRBQ8Xv08i37X_VUhnDp_Qm2xD1_F17vK8fI,3253
|
501
508
|
sglang/srt/managers/multimodal_processors/gemma3.py,sha256=G52ck_3UQGeyrtvjLqI8B0Tm8iNsyB_ahiMTAvx083U,2191
|
509
|
+
sglang/srt/managers/multimodal_processors/internvl.py,sha256=mydI4yWRMiIo6y8ZL_wxqU2IPpfVf2eR4SA-yOmK3H0,9172
|
502
510
|
sglang/srt/managers/multimodal_processors/janus_pro.py,sha256=UJoKQWsoU9kittKDwjWbG2KC12wSA-4A3DpTPhA6VoI,1854
|
503
511
|
sglang/srt/managers/multimodal_processors/kimi_vl.py,sha256=vC9OeS7gVTHzazbluiQ1I0QRKqszlqK75ghUA1rmUNc,2490
|
504
|
-
sglang/srt/managers/multimodal_processors/llava.py,sha256=
|
512
|
+
sglang/srt/managers/multimodal_processors/llava.py,sha256=APzkprLvqrQkFA6LoDemUa73FtjQL4lwGSnsx5R4vuk,8004
|
505
513
|
sglang/srt/managers/multimodal_processors/minicpm.py,sha256=uEnlsImjHBOMVNGlfBGpn1zCDLNeMY58HvJ7ZthL2N4,5698
|
506
514
|
sglang/srt/managers/multimodal_processors/mlama.py,sha256=MLiGS606LzVtdoXvjWGANx-K_7nE9J_fMVmkXN7Gz8k,1661
|
507
515
|
sglang/srt/managers/multimodal_processors/mllama4.py,sha256=50Yox7TaGrrB7iPjN1dQ_UzuY41x7VLmMcRXBhTgUvE,5592
|
516
|
+
sglang/srt/managers/multimodal_processors/pixtral.py,sha256=YG4-ufrooQnlGZ4gCnl-Scwor322oCHHbO6-SdztwpI,4064
|
508
517
|
sglang/srt/managers/multimodal_processors/qwen_vl.py,sha256=l94DOaY9vhlD-QjWVWNHUmLu48UKTb-QN9vXqrQxBgA,6907
|
509
518
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=NY62Zo0A0tLJ7ObRLOQqQcXCxoJUDZsK8f5U4dNQjKc,973
|
510
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=
|
519
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=Lyv3eUEaYnCJCLoZQhCx5WfiiUCrrS4xti3e5VROl1A,1894
|
511
520
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
512
521
|
sglang/srt/mem_cache/hiradix_cache.py,sha256=BJR-R2u5YyYIhGIxTY-3rf8Vx60XjCRU8Yhmkn2fzzM,16597
|
513
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
522
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=M1rKyPZ0TBLenO1nQgsjAwheBfMzcR3-B4hPNAEgCEQ,36358
|
514
523
|
sglang/srt/mem_cache/paged_allocator.py,sha256=BrJS0vN1k-vTSgb_M8u_1KoZFRgzgR1WRyImCTq3T0U,9770
|
515
524
|
sglang/srt/mem_cache/radix_cache.py,sha256=Lm-pco6CJ4orb9IfDpbHm5MnyK8Ya0OF1x9p88dv548,14906
|
516
|
-
sglang/srt/metrics/collector.py,sha256=
|
525
|
+
sglang/srt/metrics/collector.py,sha256=o9s4j-QC6JK_S352QVkAUkz35my57gFPWyhh3WUIfiY,19569
|
517
526
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
518
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
519
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
520
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
527
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=toZ6OvNcxWQMoPcpifWgeoeJP-fGdwySVzdLkec8Oso,26310
|
528
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=b7XH72qIpslgEpy7hyMqCXtC_fWNm_yuqVtQRk8hWPw,27731
|
529
|
+
sglang/srt/model_executor/model_runner.py,sha256=J0B6nSs8oiuizHM653c0SY5PJ9BbqUmne8igPs1bUdg,49200
|
521
530
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
522
|
-
sglang/srt/model_loader/loader.py,sha256
|
531
|
+
sglang/srt/model_loader/loader.py,sha256=-TISKGKpehU86vVyGm0xo2GALVVzQSUibi3jEisTBiw,55494
|
523
532
|
sglang/srt/model_loader/utils.py,sha256=0NaMR67fESFopaklmsleiL27XH1QUrjZW246MUu1EJ0,1369
|
524
533
|
sglang/srt/model_loader/weight_utils.py,sha256=yKnau-wH9muczoCpDTCVIqXFqz-QJmEEySplX3bMJWk,32153
|
525
534
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
526
535
|
sglang/srt/models/bert.py,sha256=kHlErDgNX_mIhfWWCnAcH_ncvYg22Y61gI34gW8GuUY,12738
|
527
536
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
528
|
-
sglang/srt/models/clip.py,sha256=
|
537
|
+
sglang/srt/models/clip.py,sha256=58m-y5lkHIGY0ypYGtgD6gImQ7yZJutYGVl-ygqbNBI,19765
|
529
538
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
530
539
|
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
531
540
|
sglang/srt/models/deepseek.py,sha256=ZnN02HdgXCB23Vno5V9UMUoOxH5HC82vNTwsVulUJ-o,17206
|
532
|
-
sglang/srt/models/deepseek_janus_pro.py,sha256=
|
533
|
-
sglang/srt/models/deepseek_nextn.py,sha256=
|
534
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
541
|
+
sglang/srt/models/deepseek_janus_pro.py,sha256=OeeI7vZbE4HGpxa8CwT6-Lbfs7J7WMQ3oBNpVJQpv3w,70450
|
542
|
+
sglang/srt/models/deepseek_nextn.py,sha256=Yy5dItwimszQsAN7EjgND2cNQ9bypJ1TtFfhqcBQJnk,5673
|
543
|
+
sglang/srt/models/deepseek_v2.py,sha256=ueqi4m3S4rj8VL49MdXmxXrNHp2rAsYCfclcjLOafHg,75767
|
535
544
|
sglang/srt/models/deepseek_vl2.py,sha256=j8BdxZsMjm6lPdbDipEIKhVIVywCP1Vl1Kl46BZ5_0Y,13147
|
536
545
|
sglang/srt/models/exaone.py,sha256=rX7J0xFt9TSt6tMIhnYMkb5KDnqTJIV4BtjPLFwQ8_8,13425
|
537
546
|
sglang/srt/models/gemma.py,sha256=4cdrPISg1VKnsuI-QPTpYvet4BrX8BMKvCIN82iLskw,12641
|
538
547
|
sglang/srt/models/gemma2.py,sha256=kqtwdo93GWKm2iBN29RoIRH2ggRm-K_80LM5btgfBLo,16395
|
539
548
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
540
549
|
sglang/srt/models/gemma3_causal.py,sha256=LfwHhF0nRD7OnmeHXXfQ7rofnFXjJI74gZiptak18RY,24924
|
541
|
-
sglang/srt/models/gemma3_mm.py,sha256=
|
550
|
+
sglang/srt/models/gemma3_mm.py,sha256=5rthHzaFNJb82IYUREwxQt4N4fDXW4lIxiptnKpVing,15246
|
542
551
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
543
552
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
544
553
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
545
554
|
sglang/srt/models/grok.py,sha256=vESZeGS4adI_JAerXIkCcTm15-CNiGeS7VHc36C6w1A,28033
|
546
|
-
sglang/srt/models/internlm2.py,sha256=
|
555
|
+
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
547
556
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
557
|
+
sglang/srt/models/internvl.py,sha256=kEzkL5tAq3skvK5D7TqhiElSIXrA6cNOd8irYV4aKhA,24927
|
548
558
|
sglang/srt/models/kimi_vl.py,sha256=YoM6CmrF4ZS0SsXKiR-_SfylKhd87ciJjno6_x5LG4o,12874
|
549
559
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
550
|
-
sglang/srt/models/llama.py,sha256
|
551
|
-
sglang/srt/models/llama4.py,sha256=
|
560
|
+
sglang/srt/models/llama.py,sha256=-NC9EL9R8iJqaRrkMLewvTP3sgC_f07AHmGBVEdKmQ8,27149
|
561
|
+
sglang/srt/models/llama4.py,sha256=EZdosYTrzEX0oYnWqocTzB4n7U9_V8fIgJqGxrJn268,19385
|
552
562
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
553
563
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
554
564
|
sglang/srt/models/llama_eagle3.py,sha256=KCvUrWn17t7T28G60HwMyy99iB9AbdbPnS2el9n3r6o,6804
|
555
565
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
556
566
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
557
|
-
sglang/srt/models/llava.py,sha256=
|
567
|
+
sglang/srt/models/llava.py,sha256=b9WcshvSqz1cqbuOq1tVTKH5J9D5PN5bBYrWzVKIQzo,37116
|
558
568
|
sglang/srt/models/llavavid.py,sha256=q0lHlRnoYHKJZsWnkIQdd6dYAQ26t7XsmrqA0zDGmZc,12829
|
559
569
|
sglang/srt/models/minicpm.py,sha256=m5HFsSJj0Po09LY9R6qj6K4gceqWDMOePz3NDGgMGT4,14691
|
560
570
|
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
561
571
|
sglang/srt/models/minicpmo.py,sha256=BAiFR78L0j5WDZtOrUf6JgUe9DZs9huIsfQ_4RzUbdA,76319
|
562
|
-
sglang/srt/models/minicpmv.py,sha256=
|
572
|
+
sglang/srt/models/minicpmv.py,sha256=hSDWEcmutqOJv-xs0X_4TaNCDAWFUk71eRHLm9sPC0U,40564
|
563
573
|
sglang/srt/models/mistral.py,sha256=EYifJUUzN2Z2-iL37eJiNZF_DB0H4pa0mKlgYRIxM70,838
|
564
|
-
sglang/srt/models/mixtral.py,sha256=
|
574
|
+
sglang/srt/models/mixtral.py,sha256=n-Pz7fyWE4m6Uh7sjzAYKNr5Wy4QUj5Yekl0qiCwQI8,17055
|
565
575
|
sglang/srt/models/mixtral_quant.py,sha256=-kQw9r8KcLdO8SNN9RKXzrGq9Q2Al9l9cWHi1VrZSRM,15260
|
566
|
-
sglang/srt/models/mllama.py,sha256=
|
576
|
+
sglang/srt/models/mllama.py,sha256=sOuP3Od3h9_uh_oxDN5rj4CzhZjg82PyElfBHuTxzUQ,39768
|
567
577
|
sglang/srt/models/mllama4.py,sha256=ejuhIVX0MDojdB5EPR-V-Qd_E9st8KYjnjyeArFbdFs,9084
|
568
578
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
569
579
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
570
580
|
sglang/srt/models/olmoe.py,sha256=TMzt-yB891bvA4X50xL0NjNnFYSx9imlA7N1EG8KNK0,15949
|
571
|
-
sglang/srt/models/phi3_small.py,sha256=
|
581
|
+
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
582
|
+
sglang/srt/models/pixtral.py,sha256=Iu7OTvM_nnApk1VjpUb1ucPBU2F1Kov5w6ddYn7gGqE,16983
|
572
583
|
sglang/srt/models/qwen.py,sha256=xYkVmMZS2uMqWhfndc8EYm0olpKFnggfuMp_6aobVi4,10758
|
573
584
|
sglang/srt/models/qwen2.py,sha256=ab912Yyk0aXOzI-wrxqN-sNF3bTVkNxB8P2uNcOCv9U,16394
|
574
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
585
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=LQee0Yuz6XzKiIFZQBUgRuDN2aX_CqvoxHx7w5a35ww,22603
|
575
586
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
576
587
|
sglang/srt/models/qwen2_eagle.py,sha256=Iz0HWL2FgSD3FqoFhfYmbIZeEYkPTJ96lYbkncmHJX4,4644
|
577
588
|
sglang/srt/models/qwen2_moe.py,sha256=iG0d2WwUosOFR9w2YGM9CfvZ1NG-rhse3OUTwSs8a6Q,18567
|
578
589
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
579
|
-
sglang/srt/models/qwen2_vl.py,sha256=
|
590
|
+
sglang/srt/models/qwen2_vl.py,sha256=X18_Smisiz6zQHUK4h7-ho8poRKWjUZisjB5LuUwYGk,20946
|
580
591
|
sglang/srt/models/qwen3.py,sha256=reaowGkotYAGHS5zTCWrvnyxtu92QKus19n-2amtMa4,12358
|
581
592
|
sglang/srt/models/qwen3_moe.py,sha256=A9Z3OhJqld1sJUDsHymgGxib4lMCMTKxF8iIzHDGdNo,15877
|
582
593
|
sglang/srt/models/registry.py,sha256=inKh9iwOp3LFYm3nqujg-OtABClOP-ifc1stA9cZegA,3434
|
583
|
-
sglang/srt/models/roberta.py,sha256=
|
594
|
+
sglang/srt/models/roberta.py,sha256=77H_-9jtjqpHlpQhBuZXs7RUG-dSjauDkpHhFe61DpE,6320
|
584
595
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
585
|
-
sglang/srt/models/torch_native_llama.py,sha256=
|
596
|
+
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
597
|
+
sglang/srt/models/xiaomi_mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
586
598
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
587
599
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
588
600
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
589
|
-
sglang/srt/openai_api/adapter.py,sha256=
|
590
|
-
sglang/srt/openai_api/protocol.py,sha256=
|
601
|
+
sglang/srt/openai_api/adapter.py,sha256=rTVMbR6jbY-lbMZL_VvWF-3E6FQrD2nb0HMg2OrBP88,77748
|
602
|
+
sglang/srt/openai_api/protocol.py,sha256=CsMwbu09RzmdZ5d6nrZ5di-5_kN1g8452kKBlX9sF6c,14353
|
591
603
|
sglang/srt/platforms/interface.py,sha256=hym3iooBB4C8if5hDZezgVN6h4NIOu7sg2ZUBIV6XmM,11246
|
592
|
-
sglang/srt/sampling/custom_logit_processor.py,sha256=
|
593
|
-
sglang/srt/sampling/sampling_batch_info.py,sha256=
|
594
|
-
sglang/srt/sampling/sampling_params.py,sha256=
|
604
|
+
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
605
|
+
sglang/srt/sampling/sampling_batch_info.py,sha256=VjOQpiXsY2vlTPtSb0T4piXIEtE54QefDpTVSDJ7bXE,11988
|
606
|
+
sglang/srt/sampling/sampling_params.py,sha256=tfUwWgxu6JWXsOClX_MFGTfetgRE63CQZsIpOhnWcoE,6013
|
595
607
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
596
608
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
597
609
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
598
610
|
sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZxBH5s_Cj82umyCzYk,5721
|
599
611
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
600
612
|
sglang/srt/speculative/build_eagle_tree.py,sha256=lt4sXUehPi26MT2-2Z0VivtF6AP7kirSaEO_u-YJ4J4,11670
|
601
|
-
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=
|
602
|
-
sglang/srt/speculative/eagle_utils.py,sha256=
|
603
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
613
|
+
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=zQl6o6_T08UWIzkZbMghwVy_O2pLOyAYreM9VmyHRmY,9298
|
614
|
+
sglang/srt/speculative/eagle_utils.py,sha256=DKYmQrO1Mg4i_8e-7YpbVtDifMWxMkAG3rATRh9gQOQ,28694
|
615
|
+
sglang/srt/speculative/eagle_worker.py,sha256=M3vSOd2MHzECAcWogFuGjdYt-AGuHFqfODQDl_Bo6qE,27012
|
604
616
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
605
617
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
606
|
-
sglang/test/few_shot_gsm8k.py,sha256=
|
607
|
-
sglang/test/few_shot_gsm8k_engine.py,sha256=
|
608
|
-
sglang/test/run_eval.py,sha256=
|
609
|
-
sglang/test/runners.py,sha256=
|
610
|
-
sglang/test/send_one.py,sha256=
|
611
|
-
sglang/test/simple_eval_common.py,sha256=
|
618
|
+
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
619
|
+
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
620
|
+
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
621
|
+
sglang/test/runners.py,sha256=ryQXb7Jpg_ewqLSF9ZSy7BAwcB1gGeTBlw9MeknzTxE,30699
|
622
|
+
sglang/test/send_one.py,sha256=zIgnesgLDI3hcoZbYv4lpmizN44ZRmhShI2FbQauLrs,5003
|
623
|
+
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
612
624
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
613
|
-
sglang/test/simple_eval_humaneval.py,sha256=
|
625
|
+
sglang/test/simple_eval_humaneval.py,sha256=s8YuKIBkNUEOBP4XKsTMRdXGv5aRhl0oJyl-89lGk1w,5687
|
614
626
|
sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
|
615
627
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
616
628
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
617
629
|
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
618
|
-
sglang/test/test_block_fp8.py,sha256=
|
630
|
+
sglang/test/test_block_fp8.py,sha256=bsV6Y_tCUF2ROEmuPDegNmHzGF-T4AgOvH7eYmAmKtA,21604
|
619
631
|
sglang/test/test_block_fp8_ep.py,sha256=N1rvqbPErBaFFpeAw8TLYXGNZOoG7cfIBP2p5XbSyMo,10806
|
620
632
|
sglang/test/test_custom_ops.py,sha256=2bSo9P5_rJZYFq8Y8IKRimDfFyZZGJluhL7Ngny0Pf4,5571
|
633
|
+
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
621
634
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
622
635
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
623
|
-
sglang/test/test_programs.py,sha256=
|
624
|
-
sglang/test/test_utils.py,sha256=
|
636
|
+
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
637
|
+
sglang/test/test_utils.py,sha256=XijnLXyC7t1Kfg_yz3Y426DgQx8PYsE8iOesdHLAPY8,35032
|
625
638
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
626
639
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
627
640
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
628
641
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=er0i3KGHMkw-4UZB1GCFd4oYwRcXfU5wpO1ORqpNGGA,7626
|
629
|
-
sglang-0.4.6.
|
630
|
-
sglang-0.4.6.
|
631
|
-
sglang-0.4.6.
|
632
|
-
sglang-0.4.6.
|
633
|
-
sglang-0.4.6.
|
642
|
+
sglang-0.4.6.post4.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
643
|
+
sglang-0.4.6.post4.dist-info/METADATA,sha256=LYS-QShEa42mO05m4fh0JjTDKD9a4rKtxYaB2vNK_jk,26006
|
644
|
+
sglang-0.4.6.post4.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
|
645
|
+
sglang-0.4.6.post4.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
646
|
+
sglang-0.4.6.post4.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|