sglang 0.4.9.post2__py3-none-any.whl → 0.4.9.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/bench_one_batch.py +2 -1
- sglang/eval/loogle_eval.py +7 -0
- sglang/srt/configs/deepseekvl2.py +11 -2
- sglang/srt/configs/internvl.py +3 -0
- sglang/srt/configs/janus_pro.py +3 -0
- sglang/srt/configs/model_config.py +9 -7
- sglang/srt/configs/update_config.py +3 -1
- sglang/srt/conversation.py +1 -0
- sglang/srt/custom_op.py +5 -2
- sglang/srt/disaggregation/decode.py +9 -1
- sglang/srt/disaggregation/mooncake/conn.py +44 -56
- sglang/srt/distributed/parallel_state.py +33 -0
- sglang/srt/entrypoints/engine.py +30 -26
- sglang/srt/entrypoints/openai/serving_chat.py +21 -2
- sglang/srt/eplb/expert_location_dispatch.py +1 -1
- sglang/srt/function_call/function_call_parser.py +2 -0
- sglang/srt/function_call/qwen3_detector.py +150 -0
- sglang/srt/hf_transformers_utils.py +0 -1
- sglang/srt/layers/activation.py +13 -0
- sglang/srt/layers/attention/flashattention_backend.py +3 -3
- sglang/srt/layers/attention/flashinfer_backend.py +40 -1
- sglang/srt/layers/linear.py +13 -102
- sglang/srt/layers/moe/ep_moe/kernels.py +4 -2
- sglang/srt/layers/moe/ep_moe/layer.py +23 -402
- sglang/srt/layers/moe/fused_moe_native.py +7 -47
- sglang/srt/layers/moe/fused_moe_triton/__init__.py +4 -4
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +146 -0
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +35 -45
- sglang/srt/layers/moe/fused_moe_triton/layer.py +14 -396
- sglang/srt/layers/moe/topk.py +187 -12
- sglang/srt/layers/quantization/__init__.py +20 -134
- sglang/srt/layers/quantization/awq.py +578 -11
- sglang/srt/layers/quantization/awq_triton.py +339 -0
- sglang/srt/layers/quantization/base_config.py +85 -10
- sglang/srt/layers/quantization/blockwise_int8.py +17 -55
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py +13 -11
- sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +24 -73
- sglang/srt/layers/quantization/fp8.py +273 -62
- sglang/srt/layers/quantization/fp8_kernel.py +210 -46
- sglang/srt/layers/quantization/fp8_utils.py +2 -2
- sglang/srt/layers/quantization/gptq.py +501 -143
- sglang/srt/layers/quantization/marlin_utils.py +790 -0
- sglang/srt/layers/quantization/modelopt_quant.py +26 -108
- sglang/srt/layers/quantization/moe_wna16.py +45 -49
- sglang/srt/layers/quantization/petit.py +252 -0
- sglang/srt/layers/quantization/petit_utils.py +104 -0
- sglang/srt/layers/quantization/qoq.py +7 -6
- sglang/srt/layers/quantization/scalar_type.py +352 -0
- sglang/srt/layers/quantization/unquant.py +422 -0
- sglang/srt/layers/quantization/utils.py +343 -3
- sglang/srt/layers/quantization/w4afp8.py +8 -4
- sglang/srt/layers/quantization/w8a8_fp8.py +17 -51
- sglang/srt/layers/quantization/w8a8_int8.py +51 -115
- sglang/srt/layers/vocab_parallel_embedding.py +1 -41
- sglang/srt/lora/lora.py +0 -4
- sglang/srt/lora/lora_manager.py +87 -53
- sglang/srt/lora/mem_pool.py +81 -33
- sglang/srt/lora/utils.py +12 -5
- sglang/srt/managers/cache_controller.py +241 -0
- sglang/srt/managers/io_struct.py +41 -29
- sglang/srt/managers/mm_utils.py +7 -8
- sglang/srt/managers/schedule_batch.py +150 -110
- sglang/srt/managers/schedule_policy.py +68 -27
- sglang/srt/managers/scheduler.py +243 -61
- sglang/srt/managers/scheduler_output_processor_mixin.py +22 -4
- sglang/srt/managers/tokenizer_manager.py +11 -3
- sglang/srt/managers/tp_worker.py +14 -0
- sglang/srt/managers/tp_worker_overlap_thread.py +11 -0
- sglang/srt/mem_cache/allocator.py +7 -16
- sglang/srt/mem_cache/base_prefix_cache.py +14 -2
- sglang/srt/mem_cache/chunk_cache.py +5 -2
- sglang/srt/mem_cache/hicache_storage.py +152 -0
- sglang/srt/mem_cache/hiradix_cache.py +179 -4
- sglang/srt/mem_cache/memory_pool.py +16 -1
- sglang/srt/mem_cache/memory_pool_host.py +41 -2
- sglang/srt/mem_cache/radix_cache.py +26 -0
- sglang/srt/mem_cache/swa_radix_cache.py +1025 -0
- sglang/srt/metrics/collector.py +9 -0
- sglang/srt/model_executor/cuda_graph_runner.py +5 -6
- sglang/srt/model_executor/forward_batch_info.py +14 -1
- sglang/srt/model_executor/model_runner.py +109 -22
- sglang/srt/model_loader/loader.py +7 -1
- sglang/srt/model_loader/utils.py +4 -4
- sglang/srt/models/clip.py +1 -1
- sglang/srt/models/deepseek.py +9 -6
- sglang/srt/models/deepseek_janus_pro.py +1 -1
- sglang/srt/models/deepseek_v2.py +191 -171
- sglang/srt/models/deepseek_vl2.py +5 -5
- sglang/srt/models/gemma.py +48 -0
- sglang/srt/models/gemma2.py +52 -0
- sglang/srt/models/gemma3_causal.py +63 -0
- sglang/srt/models/gemma3_mm.py +1 -1
- sglang/srt/models/gemma3n_mm.py +2 -4
- sglang/srt/models/granitemoe.py +385 -0
- sglang/srt/models/grok.py +9 -3
- sglang/srt/models/hunyuan.py +63 -16
- sglang/srt/models/internvl.py +1 -1
- sglang/srt/models/kimi_vl.py +1 -1
- sglang/srt/models/llama.py +41 -0
- sglang/srt/models/llama4.py +11 -11
- sglang/srt/models/llava.py +2 -2
- sglang/srt/models/llavavid.py +1 -1
- sglang/srt/models/minicpm.py +0 -2
- sglang/srt/models/minicpmo.py +3 -7
- sglang/srt/models/minicpmv.py +1 -1
- sglang/srt/models/mistral.py +1 -1
- sglang/srt/models/mixtral.py +9 -2
- sglang/srt/models/mllama.py +3 -5
- sglang/srt/models/mllama4.py +3 -3
- sglang/srt/models/olmoe.py +8 -5
- sglang/srt/models/persimmon.py +330 -0
- sglang/srt/models/phi.py +321 -0
- sglang/srt/models/phi4mm.py +44 -4
- sglang/srt/models/phi4mm_audio.py +1260 -0
- sglang/srt/models/phi4mm_utils.py +1917 -0
- sglang/srt/models/phimoe.py +9 -3
- sglang/srt/models/qwen.py +37 -0
- sglang/srt/models/qwen2.py +41 -0
- sglang/srt/models/qwen2_5_vl.py +4 -4
- sglang/srt/models/qwen2_audio.py +1 -1
- sglang/srt/models/qwen2_moe.py +53 -5
- sglang/srt/models/qwen2_vl.py +4 -4
- sglang/srt/models/qwen3.py +65 -1
- sglang/srt/models/qwen3_moe.py +56 -18
- sglang/srt/models/vila.py +1 -1
- sglang/srt/multimodal/processors/base_processor.py +91 -97
- sglang/srt/multimodal/processors/clip.py +21 -19
- sglang/srt/multimodal/processors/deepseek_vl_v2.py +8 -26
- sglang/srt/multimodal/processors/gemma3.py +13 -17
- sglang/srt/multimodal/processors/gemma3n.py +19 -23
- sglang/srt/multimodal/processors/internvl.py +9 -10
- sglang/srt/multimodal/processors/janus_pro.py +12 -27
- sglang/srt/multimodal/processors/kimi_vl.py +12 -14
- sglang/srt/multimodal/processors/llava.py +4 -2
- sglang/srt/multimodal/processors/minicpm.py +35 -44
- sglang/srt/multimodal/processors/mlama.py +21 -18
- sglang/srt/multimodal/processors/mllama4.py +4 -5
- sglang/srt/multimodal/processors/phi4mm.py +63 -39
- sglang/srt/multimodal/processors/pixtral.py +14 -35
- sglang/srt/multimodal/processors/qwen_audio.py +65 -0
- sglang/srt/multimodal/processors/qwen_vl.py +16 -21
- sglang/srt/multimodal/processors/vila.py +14 -14
- sglang/srt/sampling/sampling_params.py +8 -1
- sglang/srt/server_args.py +393 -230
- sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +9 -1
- sglang/srt/two_batch_overlap.py +1 -0
- sglang/srt/utils.py +27 -1
- sglang/test/runners.py +14 -3
- sglang/test/test_block_fp8.py +8 -3
- sglang/test/test_block_fp8_ep.py +1 -1
- sglang/test/test_custom_ops.py +12 -7
- sglang/test/test_cutlass_w4a8_moe.py +1 -3
- sglang/test/test_fp4_moe.py +1 -3
- sglang/test/test_marlin_moe.py +286 -0
- sglang/test/test_marlin_utils.py +171 -0
- sglang/test/test_utils.py +35 -0
- sglang/version.py +1 -1
- {sglang-0.4.9.post2.dist-info → sglang-0.4.9.post3.dist-info}/METADATA +8 -8
- {sglang-0.4.9.post2.dist-info → sglang-0.4.9.post3.dist-info}/RECORD +166 -146
- sglang/srt/layers/quantization/quant_utils.py +0 -166
- sglang/srt/managers/multimodal_processors/qwen_audio.py +0 -94
- {sglang-0.4.9.post2.dist-info → sglang-0.4.9.post3.dist-info}/WHEEL +0 -0
- {sglang-0.4.9.post2.dist-info → sglang-0.4.9.post3.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.9.post2.dist-info → sglang-0.4.9.post3.dist-info}/top_level.txt +0 -0
@@ -1,7 +1,7 @@
|
|
1
1
|
sglang/__init__.py,sha256=x1v8748WXS2BAptWAd5fR3YBEkngC7e_P_rkCNuNCGg,1702
|
2
2
|
sglang/api.py,sha256=rcp3GeoyZhmJ0GDLPRkuZNcxd0TBJy_wfUDpcmQoqW8,7210
|
3
3
|
sglang/bench_offline_throughput.py,sha256=TwgXZYmwPaHVsdPtNU9LO0p1tr5OOKLy9wYgrfGAlFU,14056
|
4
|
-
sglang/bench_one_batch.py,sha256=
|
4
|
+
sglang/bench_one_batch.py,sha256=ETz7G8HazZ0iVkWVLrzgNEENnJ_xR_8UCzzRLm-AbpQ,19462
|
5
5
|
sglang/bench_one_batch_server.py,sha256=LS1BRmFwP67IpYlU5wmkWjqquiA5drvtWe-fwHnFSKI,14170
|
6
6
|
sglang/bench_serving.py,sha256=nOjDnqOKDezDvtCvEhC1_FAoWVkir38bSaEIcSGGVZg,71748
|
7
7
|
sglang/check_env.py,sha256=qDMIG2rCNBH1yKnxQmF-Bp10oiFMUKMgfZLHZYOmdSY,8412
|
@@ -10,9 +10,9 @@ sglang/global_config.py,sha256=xzLdk8W53fneFblNh8iIjGF9C3-7mnzR1-LleD9Btxg,1495
|
|
10
10
|
sglang/launch_server.py,sha256=mDXfwha8LHpWQJekcCosR98QhCQsbmilsBlI5jAIgg0,420
|
11
11
|
sglang/profiler.py,sha256=tEHzHerXC-ymk4OrkoUcMbgcGHmb8VESthsNSP2Yx9w,4417
|
12
12
|
sglang/utils.py,sha256=leKs-YyX1_Jk216yoKX-KRYx_EbLiuemsHbD31xSjMw,16445
|
13
|
-
sglang/version.py,sha256=
|
13
|
+
sglang/version.py,sha256=l7iWzcwTcItFAUU_b9YsWRVypWGj8cPQTjULXXXSKcI,28
|
14
14
|
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
15
|
-
sglang/eval/loogle_eval.py,sha256
|
15
|
+
sglang/eval/loogle_eval.py,sha256=-CC2s2kh5qUoDrHRkQVkC_jNvBgNojXbf456ny5s78s,4557
|
16
16
|
sglang/lang/chat_template.py,sha256=HKlx7snSWFED8GKF5ex79sQrPWFw5TSXQM0_LsiD9Bc,20552
|
17
17
|
sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
|
18
18
|
sglang/lang/compiler.py,sha256=MAuzoOOpb98njJ7Io2SDmFkhTroDYiq0te0ZpfHkMY4,7597
|
@@ -30,34 +30,34 @@ sglang/srt/_custom_ops.py,sha256=0lJRMTKTjoxJPh1qQnnMY02Z3SyBDi7LJI34IBLQsgQ,446
|
|
30
30
|
sglang/srt/aio_rwlock.py,sha256=6LYtOdeTUY3hkfa1dmYkgsaF2ttrwIF3hUWz2AZ2fqw,2970
|
31
31
|
sglang/srt/code_completion_parser.py,sha256=KFa95OU0TeVjJkOqIgS4xV3kaJ5dFWOmAAgISyc1oEc,3803
|
32
32
|
sglang/srt/constants.py,sha256=0i-tEwG2BSYNDy96MxnGHV5HnBELkYcnsVGsE-R18o0,93
|
33
|
-
sglang/srt/conversation.py,sha256=
|
34
|
-
sglang/srt/custom_op.py,sha256=
|
33
|
+
sglang/srt/conversation.py,sha256=_dDqfoULuZdDN41-3I-3oF5KVo35E9lv0KPjgAaG-mY,40399
|
34
|
+
sglang/srt/custom_op.py,sha256=7OPQAZe3PqDXk-xM0Wxl7pm9cazilNJfkNiYIWztWgI,3198
|
35
35
|
sglang/srt/debug_utils.py,sha256=slaFOY4BYDBFatkfu8FZlzai-u4LFS-5GUzdr-t50zE,2241
|
36
|
-
sglang/srt/hf_transformers_utils.py,sha256=
|
36
|
+
sglang/srt/hf_transformers_utils.py,sha256=UiGjp70ZpTaZDJ99Roc-2DTkxV3gR-2oJjjaNY9Ekh4,12391
|
37
37
|
sglang/srt/jinja_template_utils.py,sha256=0c6nQjkGukmyXsqQ9r85R5QK9CafnjqXyrXF4K3aFhE,7177
|
38
38
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
39
39
|
sglang/srt/operations.py,sha256=ddQ8KO63L73OciaR8MZ9h2h83gKVY4-WuWgeEGowPJA,5346
|
40
40
|
sglang/srt/operations_strategy.py,sha256=Pwd2sKeRtKh9WJXgzlNr2tU9y6YMcI3MDLbatHqlMws,7145
|
41
41
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
42
42
|
sglang/srt/reasoning_parser.py,sha256=DkZrFhkJ9qe7w46fTnM9sqhXwTDgZxD4qPdGka-Dly8,7579
|
43
|
-
sglang/srt/server_args.py,sha256=
|
43
|
+
sglang/srt/server_args.py,sha256=2QFUu2xdPbIC_2Zf6BaBF_Ro9tSriUkvNp6P5VBZVOY,83290
|
44
44
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
45
|
-
sglang/srt/two_batch_overlap.py,sha256=
|
46
|
-
sglang/srt/utils.py,sha256=
|
45
|
+
sglang/srt/two_batch_overlap.py,sha256=QxM1VzpAuiWniqsoHztDLTTfTsDVk4Lmh2pVq5flHxY,28610
|
46
|
+
sglang/srt/utils.py,sha256=8QMSz7KDKbOuvtDLteVKLKOOyhmEhMYxvxBM670XPW4,92419
|
47
47
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
48
48
|
sglang/srt/configs/__init__.py,sha256=8EcVRP95epZ49DxBa6LgKWt7eO3Qe7Hrr3V1c6HkMnY,553
|
49
49
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
50
50
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
51
|
-
sglang/srt/configs/deepseekvl2.py,sha256=
|
51
|
+
sglang/srt/configs/deepseekvl2.py,sha256=sYMmoy5_LlDXht7MTi4QGYOaiE8iMGUO44bnuOu4i8I,23683
|
52
52
|
sglang/srt/configs/device_config.py,sha256=kdwFrk5myAURxdp4rSr8ANpBpSJfuBDoT-kuCyuscRs,442
|
53
53
|
sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
|
54
|
-
sglang/srt/configs/internvl.py,sha256=
|
55
|
-
sglang/srt/configs/janus_pro.py,sha256=
|
54
|
+
sglang/srt/configs/internvl.py,sha256=Ws-LNun1s5kaATSp8H0XNbUrwMa9Be9axZ6hfig_F7I,27697
|
55
|
+
sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsrKI,19156
|
56
56
|
sglang/srt/configs/kimi_vl.py,sha256=4W7VQI3pr888ZsFA2SqCQo4mI0seXTOrGQ-x3oTvWew,1358
|
57
57
|
sglang/srt/configs/kimi_vl_moonvit.py,sha256=hx2Rt4JSFbvy2HUTeLjBpge87m8M6ITAhqsgdNf_Jd4,1163
|
58
58
|
sglang/srt/configs/load_config.py,sha256=qs-AxuplouBx2tsv9KGBOLZPbwzuVA4vbktbGP_cRp8,3309
|
59
|
-
sglang/srt/configs/model_config.py,sha256=
|
60
|
-
sglang/srt/configs/update_config.py,sha256=
|
59
|
+
sglang/srt/configs/model_config.py,sha256=6X0aVKcWTJfu5Lw6gCtKodJVg7EUXcr2Js_NuGYeUYk,28401
|
60
|
+
sglang/srt/configs/update_config.py,sha256=D-myV9Ombwp6wTF0RX9qUO6m5rxFiUcyse32FQADG28,4787
|
61
61
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
62
62
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
63
63
|
sglang/srt/connector/base_connector.py,sha256=i6i1TIzsz4NbSEkrdMPq-urb2sN2aLAx8dazga4gB9U,2833
|
@@ -74,7 +74,7 @@ sglang/srt/constrained/outlines_jump_forward.py,sha256=Gyubp-FVetxd6wP4FA_kD6cCX
|
|
74
74
|
sglang/srt/constrained/reasoner_grammar_backend.py,sha256=YFxWuOTTo4e6cGhxnaBwuwli6f8FTUJtszib8dBq_8I,3207
|
75
75
|
sglang/srt/constrained/xgrammar_backend.py,sha256=u9Ao-XX22UzALkATEAR_-0EoyBTxMTJV590qd9LAUHM,7906
|
76
76
|
sglang/srt/constrained/triton_ops/bitmask_ops.py,sha256=WjTen9iuuFWLzkE1mAHQZB9_7aIy5QH8Wjf-lB-Fams,4614
|
77
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
77
|
+
sglang/srt/disaggregation/decode.py,sha256=P-0OyFjjDfthEVhlJugdscWST_uoOVmHZlSlx9NYLmE,34242
|
78
78
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=8UdNaj8KKMLV5Cydhw8gnHM-zRrnKM_AAd3Qc-SRfWg,5648
|
79
79
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
80
80
|
sglang/srt/disaggregation/launch_lb.py,sha256=mcbAztN4gnHevw_T5R2_nWsymsDEY9vHkm7OJ1vr6cc,4211
|
@@ -92,13 +92,13 @@ sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeK
|
|
92
92
|
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
93
93
|
sglang/srt/disaggregation/fake/conn.py,sha256=oD1DArn1yDFZCu-X6p93uSLlAXEkt9lYxERICMznxGw,2286
|
94
94
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
95
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
95
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=ml3Ke6md9YYjG6yI4FAufF_642sbp2lOHVemF9Ww_Y0,60451
|
96
96
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=a3pki0d7QauTn6slt7gVxjicABP6Uo4Ztt0wEXR9dZc,4687
|
97
97
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
98
98
|
sglang/srt/disaggregation/nixl/conn.py,sha256=cXqWU2Gbi6E2LS0MznEcgFCrwONhYxBtD-zE9DU32z0,20333
|
99
99
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
100
100
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
101
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
101
|
+
sglang/srt/distributed/parallel_state.py,sha256=nNLIRLFnLH4CtZqAt0CsuwyuTLgCrL5WjLDlS1-hj-4,56212
|
102
102
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
103
103
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
104
104
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=qje-PQ3v8yaV-oYVLPws1mgIlXVsGKFCOvXHmSe8ZXg,19624
|
@@ -111,13 +111,13 @@ sglang/srt/distributed/device_communicators/pynccl_wrapper.py,sha256=LblisImY9d6
|
|
111
111
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=d8mykYmXM1lfbPm8GNtqCF0Un_pdXYjbNmsgoVFyyow,20874
|
112
112
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
113
113
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
114
|
-
sglang/srt/entrypoints/engine.py,sha256
|
114
|
+
sglang/srt/entrypoints/engine.py,sha256=-J3rcOwCClya3h-jf6WjGDxLmJowJoZA4RVF9aRwwX0,31816
|
115
115
|
sglang/srt/entrypoints/http_server.py,sha256=pUZgA7ILuRynIY3Cs2nbFoXSnZ7ohsMauF_RBtl-V_s,37538
|
116
116
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
117
117
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
118
118
|
sglang/srt/entrypoints/openai/protocol.py,sha256=oAd5u_J6Wk9gzXVPS-Ps8VaxkhmMXyIuH1KZ73pEOvQ,19083
|
119
119
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=5NJ2S_6B2NFSwn4nLp6eaeJ5iC3IcQzMEY9lW_gPcdA,5246
|
120
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
120
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=o3-phSK6gHuG11eYpUbVJhz4Fq5yZeGRwQzIDhwdc10,37221
|
121
121
|
sglang/srt/entrypoints/openai/serving_completions.py,sha256=emIutVmnJgOgGRuAqdB80-kVHUfQbE67n1VS-76o4QY,16690
|
122
122
|
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=hqPt2ELpT1yQ8sBXo801aLJ3sExoPXs_K5ZQtC2vpAs,6274
|
123
123
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
@@ -128,7 +128,7 @@ sglang/srt/eplb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
128
128
|
sglang/srt/eplb/eplb_manager.py,sha256=Wt7w4L5g1BSsXx1mqoGo8WjkB55f4nGB4KqC3y_ijl8,3394
|
129
129
|
sglang/srt/eplb/expert_distribution.py,sha256=N2wcIzQo9nzPpH5jR63RH7iB00XvH4R8OGp-rR_07f4,31332
|
130
130
|
sglang/srt/eplb/expert_location.py,sha256=unthN8w37bvxf_4Z1xNi-Gi4SGnZbTBbMpHC1be9QMI,16665
|
131
|
-
sglang/srt/eplb/expert_location_dispatch.py,sha256=
|
131
|
+
sglang/srt/eplb/expert_location_dispatch.py,sha256=ErUBjzDffcF0FgPI-Xv90RDrtKnQwNB9woouZFS2C7k,4126
|
132
132
|
sglang/srt/eplb/expert_location_updater.py,sha256=oVIUYzji6BFEd2AgeRcM6kwEqLwwD3_PEEv3EyWIydk,21100
|
133
133
|
sglang/srt/eplb/eplb_algorithms/__init__.py,sha256=c6fo4qM8N0p5DyyfGp9fxqc2wkxvzSJBzJFRG1I1leg,1959
|
134
134
|
sglang/srt/eplb/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9enSt426uUTKeiq4,8340
|
@@ -139,21 +139,22 @@ sglang/srt/function_call/base_format_detector.py,sha256=eMSqbx99YPm2m_ChLafFRuLO
|
|
139
139
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
140
140
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=XudIiIt2Mejokg6qOkX7vYS-3XIFstOBHv-m-Q5fBLQ,8970
|
141
141
|
sglang/srt/function_call/ebnf_composer.py,sha256=1r5UPEkUeMCug-P-c1mAZbJPgEXU8hR-fDLdYG5Q-wo,13585
|
142
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
142
|
+
sglang/srt/function_call/function_call_parser.py,sha256=H0euMLfFJVPdKVjSJ0STsNdKEmdCfXExrug1LOXHxS4,7889
|
143
143
|
sglang/srt/function_call/kimik2_detector.py,sha256=wb--wnAp-ZtWeIJZM1dS33GNu-K9lGxvrFbtp-UmGVk,8978
|
144
144
|
sglang/srt/function_call/llama32_detector.py,sha256=EHYGAy1NCIxFWKdSQByPxyJgFaFRCtGdgj4ntEAgi00,3619
|
145
145
|
sglang/srt/function_call/mistral_detector.py,sha256=xNuVl2vDXVYbXyiXLkJZ9VM6njcwlS9EqryR1eJbMr4,4462
|
146
146
|
sglang/srt/function_call/pythonic_detector.py,sha256=rtXSflE4w993a4OqphWG-WQzvwRz0v3dfgHOnte1fpI,8731
|
147
147
|
sglang/srt/function_call/qwen25_detector.py,sha256=9JfZem_5nw91Og2biwq8eIpUQjy_3kFz4TQI8Lc3Vow,4882
|
148
|
+
sglang/srt/function_call/qwen3_detector.py,sha256=FWoXfa1dkvLT-zGmjxJUJm_BlCErZI23eWz3g7SwFP8,5361
|
148
149
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
149
|
-
sglang/srt/layers/activation.py,sha256=
|
150
|
+
sglang/srt/layers/activation.py,sha256=W1az1HEdUCnXblPORcMZHJwrxlYAb87v4JCIYF3xJak,7594
|
150
151
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
151
152
|
sglang/srt/layers/communicator.py,sha256=yckTsQ_3SeADES7maU2bgIpzwbWu3Q3Qpxu8T8UpCoQ,20045
|
152
153
|
sglang/srt/layers/dp_attention.py,sha256=V7m_PfvHHtRMJMviIqmoyqf5VFFJLYYcynDuI5dXtAU,10275
|
153
154
|
sglang/srt/layers/elementwise.py,sha256=MyQUflyKEfPZ-BggW1Kd4hB53RFD6FXGc2S5LXjx_do,16026
|
154
155
|
sglang/srt/layers/flashinfer_comm_fusion.py,sha256=fkTcAB7qYwSWi95qI3Rqq0JUyDpJdcYkd4TYkWO01HI,5891
|
155
156
|
sglang/srt/layers/layernorm.py,sha256=ooqA-t-vY5erbKBwqnOotfDsJRTygP5E10CfzEAVF6M,8657
|
156
|
-
sglang/srt/layers/linear.py,sha256=
|
157
|
+
sglang/srt/layers/linear.py,sha256=NzjLqZrZNYcc3z2KtA9-n6pnSdBHHwU6NF_BbcAWp48,52471
|
157
158
|
sglang/srt/layers/logits_processor.py,sha256=tOPMYopEQuoLBzwbjSmU9OWFYh2mmy3ViJSbA_wpFOU,25619
|
158
159
|
sglang/srt/layers/multimodal.py,sha256=YVR69WW-2aGDcZHT8IVJ6F_LRM7wraZr8VjrPDXqDmA,2104
|
159
160
|
sglang/srt/layers/parameter.py,sha256=jCg0G-12GZqTa9gGOqEtVCsnnuBGnYg0VmF6pc6oCFg,17455
|
@@ -163,14 +164,14 @@ sglang/srt/layers/rotary_embedding.py,sha256=EhxI0E8jcTWZ2COpnku7crbW8Hew5fe_ujM
|
|
163
164
|
sglang/srt/layers/sampler.py,sha256=xNds1migup2s6b9_pS6ljkJUkvNtv7nmTGeIdOzoQ6w,11182
|
164
165
|
sglang/srt/layers/torchao_utils.py,sha256=Ws24FdRBSkTpyeyA6bQrdDm-W5wfDxKvSIPUSahyMfA,4063
|
165
166
|
sglang/srt/layers/utils.py,sha256=IWGg1Hb7c33Z3LHRPVJyUAzp3BnSid23ZWXAmJ_Jvp8,1204
|
166
|
-
sglang/srt/layers/vocab_parallel_embedding.py,sha256=
|
167
|
+
sglang/srt/layers/vocab_parallel_embedding.py,sha256=FSAxHh1w9Qz4A2_8OQfIP5qsmq1s_g-Od-VLJ4vqQPw,22355
|
167
168
|
sglang/srt/layers/attention/aiter_backend.py,sha256=7sEUgViw-xl3yok91yyOD9gTi8lQmME0g0ZiKVTCcyI,32851
|
168
169
|
sglang/srt/layers/attention/ascend_backend.py,sha256=jPCsU9_gH1iZNoZHD9nCeDdVdXqBt31LI65N55BTJPg,8250
|
169
170
|
sglang/srt/layers/attention/base_attn_backend.py,sha256=KXVcCguwXh-PSrY9Y2aUrlXXUhWdbVxqVEF2_xIMvm4,3466
|
170
171
|
sglang/srt/layers/attention/cutlass_mla_backend.py,sha256=SIR7sKCCegwzahSz82I3gsDyN5TkKoa4yG4-pBQWBi4,9813
|
171
172
|
sglang/srt/layers/attention/double_sparsity_backend.py,sha256=2ZRL_gYz14idoVqQzeQ6N77nXer0f_8_TUYw40XUUz0,9161
|
172
|
-
sglang/srt/layers/attention/flashattention_backend.py,sha256=
|
173
|
-
sglang/srt/layers/attention/flashinfer_backend.py,sha256=
|
173
|
+
sglang/srt/layers/attention/flashattention_backend.py,sha256=rYsBAsFS1qNNe-3CVIaXxWRqA3eul1jVQXvfZ_wlpwg,94076
|
174
|
+
sglang/srt/layers/attention/flashinfer_backend.py,sha256=HQp14R29hQVXYjATKPoGaHY9LJ9e1cw2k-RhBEmFxt8,51505
|
174
175
|
sglang/srt/layers/attention/flashinfer_mla_backend.py,sha256=NirRlNFxD0S2EncvvmrerIxNfuTnYpvemZV3MR5_FnU,34040
|
175
176
|
sglang/srt/layers/attention/flashmla_backend.py,sha256=5iSic5ho-lkXNas9mR3uLbXbEl-do31gc8gjR7-a79k,20711
|
176
177
|
sglang/srt/layers/attention/intel_amx_backend.py,sha256=hH9lxXs_o66_IVs58oPhRCOXGUrHbXSz82FKtHr9GO8,4092
|
@@ -189,16 +190,16 @@ sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91E
|
|
189
190
|
sglang/srt/layers/moe/cutlass_moe.py,sha256=--bNTA2BGbHeULb_XXDoRUyWWbE-doHo5K5k1T0N0WA,14323
|
190
191
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
191
192
|
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=bc8s5Oc36pCF0VozxZuqFOOU2fov-4wGPlyduye3Imk,7296
|
192
|
-
sglang/srt/layers/moe/fused_moe_native.py,sha256=
|
193
|
+
sglang/srt/layers/moe/fused_moe_native.py,sha256=SkOFgU23aZfHmLhnkVhdUWGx0-2wbo6uu9ohKBp2yOI,3486
|
193
194
|
sglang/srt/layers/moe/router.py,sha256=UrPieRvemN7Ew48gtG7DA2xhNDBRSnZxzugTEBI-0_E,12006
|
194
|
-
sglang/srt/layers/moe/topk.py,sha256=
|
195
|
+
sglang/srt/layers/moe/topk.py,sha256=zjnI1s-NevasGpyuxurGVmCXMxGNfhp5F5onGePnf5A,25256
|
195
196
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
196
|
-
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=
|
197
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
197
|
+
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=UFH-XacP3aBjAcn6_SeC641jGzjSrY0fz50IB9URix4,42706
|
198
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=0vJW7RoEJ8Y3wD3q8pk289Gx5KNSVNJBbdpveliyXyM,46910
|
198
199
|
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=aiBE3mjvWV3eBrFGH9J44tuJncQwOjRS_XeyBNCEtqM,24379
|
199
|
-
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=
|
200
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
201
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
200
|
+
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=4NXZHbCw-G-uSnNUj4up0yh3xBDPnT-x0pdoIr0lku8,831
|
201
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=YytUs8ojQ83eyw9ObVZPxjdHXcuVbkEbpe1hLvI-nJQ,62950
|
202
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=BUbo3OFiSjqs34MK09McFYqSsKguDcG6KP1905WUMFA,23933
|
202
203
|
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=hoWVdf8ry8IDGH2bfk2WW-y2S5h5haLTGanBSwkkeE0,5848
|
203
204
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
204
205
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JJN0hryyLr5Zv3dSS7C8cPFhAwTT6XxUVnBGMZvV6JA,2752
|
@@ -361,29 +362,39 @@ sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=hoWVdf8ry8ID
|
|
361
362
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
362
363
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=LNx1W_BsWZcpHomiScCRap46dV0-F7S_w3Htskoqlm8,3263
|
363
364
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=fo1akCuGoqcGwQgfh56hApgg-wLXfo9kHHksE_6m1F4,3262
|
365
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=ENDYnC1ljPNpDVHdmqR7UbgDWT1IP_55ZIQ_Oae34mI,3264
|
366
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=5UAs8Z1myw8F-5FY2HHWd5WMT2ii9X-aYIYkf3FsA8s,3269
|
367
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=941ZXJti99_GUeiylwPUWqYK8b548xuNIjv0pz9Kcqg,3262
|
368
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=rgF-KSAUXmI7QGrhMUywPVfeTxz_j8_IP4N-6bkYdak,3260
|
369
|
+
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json",sha256=7aaoi0MI2xC5ZJkflkTZAH4tawTPdmUpmcBOgOInKxs,3268
|
364
370
|
"sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=a9XJZ0XudUTebAdN5guVq-3XSvZetHIRjatO1-_0xCk,3257
|
365
|
-
sglang/srt/layers/quantization/__init__.py,sha256=
|
366
|
-
sglang/srt/layers/quantization/awq.py,sha256=
|
367
|
-
sglang/srt/layers/quantization/
|
368
|
-
sglang/srt/layers/quantization/
|
369
|
-
sglang/srt/layers/quantization/
|
370
|
-
sglang/srt/layers/quantization/
|
371
|
-
sglang/srt/layers/quantization/
|
372
|
-
sglang/srt/layers/quantization/
|
371
|
+
sglang/srt/layers/quantization/__init__.py,sha256=lMjOmhMntbY55RR5eKKLB338tdzlxGuBx-pT4f9jmIM,8130
|
372
|
+
sglang/srt/layers/quantization/awq.py,sha256=gLEOx6QoGQ0McBEURXPVidKGsdNUjqc9sJwGLQx86rE,26690
|
373
|
+
sglang/srt/layers/quantization/awq_triton.py,sha256=4XwJbRNlFmlvjbMGtWF1Wvk26Kf96162vNEmuI5Kars,11737
|
374
|
+
sglang/srt/layers/quantization/base_config.py,sha256=CiSxG5iuOa-12V9kIOh0Fu8Y7knZxfFbbNGTo6nEaRE,7173
|
375
|
+
sglang/srt/layers/quantization/blockwise_int8.py,sha256=3avetVUBjCiuYWBJQbElbVXWpx0SgsFsDc5F9F_zHgA,13879
|
376
|
+
sglang/srt/layers/quantization/fp8.py,sha256=T6Gns69ot-qE4DcxhZLoY41VG450qpbM_EbuRdRleuk,56618
|
377
|
+
sglang/srt/layers/quantization/fp8_kernel.py,sha256=1nrJvQNVZszd_SIIeOEgB2CiqyqdfVHbsBXegPiEfk4,40160
|
378
|
+
sglang/srt/layers/quantization/fp8_utils.py,sha256=6FVR6_Y8akP4ihCaGG_bLYurcC_PShPtiPgiEvGN5bE,25605
|
379
|
+
sglang/srt/layers/quantization/gptq.py,sha256=3q9xfq5sJJHcrVr9C8-l9JdcLFvwKAAfWJEfZW6CzLs,39145
|
373
380
|
sglang/srt/layers/quantization/int8_kernel.py,sha256=GfRC9FOn9exNvK4QHbUeBj3Hhv32VcyGphapFPt5b84,12625
|
374
381
|
sglang/srt/layers/quantization/int8_utils.py,sha256=YK9CS-lb_n91kNCTKK5o5apYF31V2giDg5G5VKrpcUA,2356
|
375
382
|
sglang/srt/layers/quantization/kv_cache.py,sha256=_9pF5rwvB7ta6Gdc5YKVVGbNzYwqmhIx4TrX1-xnodQ,3261
|
376
|
-
sglang/srt/layers/quantization/
|
377
|
-
sglang/srt/layers/quantization/
|
378
|
-
sglang/srt/layers/quantization/
|
379
|
-
sglang/srt/layers/quantization/
|
380
|
-
sglang/srt/layers/quantization/
|
381
|
-
sglang/srt/layers/quantization/
|
382
|
-
sglang/srt/layers/quantization/
|
383
|
-
sglang/srt/layers/quantization/
|
383
|
+
sglang/srt/layers/quantization/marlin_utils.py,sha256=ShsoxcVTYo1Es3XKp9mlQNw-TsRF_o4mHIO5MfAP5HA,25906
|
384
|
+
sglang/srt/layers/quantization/modelopt_quant.py,sha256=V6FzVSNdqHr9nYe4667AeWdRTjY3n5Tp1d41W3eCYV8,37661
|
385
|
+
sglang/srt/layers/quantization/moe_wna16.py,sha256=NGcFjiMXwfOX10dkHAY3EgZHxox2k7I402Bvwj3jW1Q,19105
|
386
|
+
sglang/srt/layers/quantization/petit.py,sha256=74Jn0eICq23v_b4rEctDaYTINtbqkdM6IXycT-_FbbI,8954
|
387
|
+
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
388
|
+
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
389
|
+
sglang/srt/layers/quantization/scalar_type.py,sha256=nBk4THjeRWMGW3hKWRdrjfQ0gwpuBxmYqapDBaRpnr4,12395
|
390
|
+
sglang/srt/layers/quantization/unquant.py,sha256=hzyGGJoclb1oANy3hYxrEK76F7V7LNjU2rd3NWDpeGg,13997
|
391
|
+
sglang/srt/layers/quantization/utils.py,sha256=mF5Hk42IHdGYi-l_1ZVHszXMY4WqgFEpOSDIlGZQ2sA,16469
|
392
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=r36F5f5tAan8omW2UYZwK7xIwZUAWYHBbwJtmIIVzIY,9672
|
393
|
+
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=I_W9A4Pnluaf-SaT8zq-tAJTt1acpxfE_kG5mqdc5cE,10250
|
394
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=VGrVELArNuyw4FEtUefaeK8ayuX7cpXj1OOqCmOCzm4,34902
|
384
395
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
385
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=
|
386
|
-
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=
|
396
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=DsPCI82A4rqI6mjKo-WorIKUweppFV7-16Qku-zW9_g,25897
|
397
|
+
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=Ss6bWLlmN9hNLbB9bdIaZFapiAJAzTaXhyf4pPwh1OY,24536
|
387
398
|
sglang/srt/layers/quantization/compressed_tensors/utils.py,sha256=mnUmKWFQUnY8bVoFHUuNVwqsfS-cefeR-ofyaihCXcY,7621
|
388
399
|
sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=HWMTnmrj-mUCRXgcOwnnXLrvrAE-ONdPTSzSImjHCMA,347
|
389
400
|
sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=tdKJC8c3SX8T3z8JL-1YCsg4ftcv55Wxt0vZrYftpX8,1635
|
@@ -546,11 +557,11 @@ sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py,sha256=BrzCCxX
|
|
546
557
|
sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py,sha256=zkMzBAqQTSwG9TlGPuwmHV1yN0v5Y_5Hgyo0CKQDVNU,741
|
547
558
|
sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py,sha256=On_uvP1ThxgQFAzOWKoteM0vIOHqmtI127A4qbPtmbc,3264
|
548
559
|
sglang/srt/lora/layers.py,sha256=FaTYf0w3zbKKKAT1nJdAzGRtxvySB6FpNKXvEi5RHH0,12958
|
549
|
-
sglang/srt/lora/lora.py,sha256=
|
560
|
+
sglang/srt/lora/lora.py,sha256=sRoU7BdlTV4cnBv1-u3QjisVR9XQrrqAsmhxdNtd8dU,9433
|
550
561
|
sglang/srt/lora/lora_config.py,sha256=qDgMTx_69jyJUl29O5FxLzYa0BMhqYVXWXfyyVOvGm0,1684
|
551
|
-
sglang/srt/lora/lora_manager.py,sha256=
|
552
|
-
sglang/srt/lora/mem_pool.py,sha256=
|
553
|
-
sglang/srt/lora/utils.py,sha256=
|
562
|
+
sglang/srt/lora/lora_manager.py,sha256=biyPbUqnkez8OnSFXXjo_da8L0vH2ux954ypJTYfrIM,21667
|
563
|
+
sglang/srt/lora/mem_pool.py,sha256=YsEJkddDhKDsCZ3f4hihhhZvyn0U1hWY07rx3zyrCPQ,12158
|
564
|
+
sglang/srt/lora/utils.py,sha256=5G0KiDEn-Zg4OgIOjWnU2ZdQGNstZswoAog9xU4GVDA,5660
|
554
565
|
sglang/srt/lora/backend/base_backend.py,sha256=EIz8I-GIrdmK4fISw3ENhbJVVITaxKfyLxHXGPU4fPs,5044
|
555
566
|
sglang/srt/lora/backend/flashinfer_backend.py,sha256=el6IAB4kTgDTbwCggmqFuukliyoapN5X6FLksG-4wJ8,4151
|
556
567
|
sglang/srt/lora/backend/triton_backend.py,sha256=uqwBGlguXX8EkCKjSPqac6SPTgcKA31u3u6HkKPQcos,2530
|
@@ -559,142 +570,149 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVh
|
|
559
570
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=iz5scFNo2YFTeiM8beWg9Z1oZI-6AM_T1wBMCQ6qp2Q,6485
|
560
571
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
561
572
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
562
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
573
|
+
sglang/srt/managers/cache_controller.py,sha256=yJaVg78tM24CxVUk5-DDFXLiiLmqELyTpPUeW0CjlPo,22116
|
563
574
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
564
575
|
sglang/srt/managers/data_parallel_controller.py,sha256=PZ-wOcAFn3PQqMB6I2vjIsFmplf0nlNl5hqTDKTHTG8,12112
|
565
576
|
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
566
|
-
sglang/srt/managers/io_struct.py,sha256=
|
567
|
-
sglang/srt/managers/mm_utils.py,sha256=
|
577
|
+
sglang/srt/managers/io_struct.py,sha256=I8DQ348J2rz7LefwXINCdaq10vaBFrBi7kSDgpQRtHs,37205
|
578
|
+
sglang/srt/managers/mm_utils.py,sha256=sHEOfM7T46btXHDArz5lS6pRL7gleAJpEz7l_z_MnWs,25476
|
568
579
|
sglang/srt/managers/multimodal_processor.py,sha256=mzCrN-8H0bE0iMO8UzxmYmhE2M1qsbVJXGdhAYcjjYA,2016
|
569
|
-
sglang/srt/managers/schedule_batch.py,sha256=
|
570
|
-
sglang/srt/managers/schedule_policy.py,sha256=
|
571
|
-
sglang/srt/managers/scheduler.py,sha256=
|
572
|
-
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=
|
580
|
+
sglang/srt/managers/schedule_batch.py,sha256=y7BCydjHSn75zVuArzX6ecWM6HJD0rv70PXXsUTwfJ4,75603
|
581
|
+
sglang/srt/managers/schedule_policy.py,sha256=BFYItMXtrsO5157tpFhYwLpZ8NSlzR4_gNZC1iE10D4,22400
|
582
|
+
sglang/srt/managers/scheduler.py,sha256=6s0vJHsbKydAnH5E2e7TGr_sVFNTJH4GTbQRFZVLN0w,120941
|
583
|
+
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=Ei-9lyfrSQAlL9_ULuJLAhA7qpvUzjsBDzBBTDdnt4Q,31394
|
573
584
|
sglang/srt/managers/session_controller.py,sha256=dzlMNZlo20FTSl64QqK7y7pElsdCy8ICOWWBPTBVwgs,6040
|
574
585
|
sglang/srt/managers/template_manager.py,sha256=RrwRA2oqId_PMQ98qJQGwIxMroOxiorl2sGC9ARou_0,8543
|
575
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
576
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
577
|
-
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=
|
586
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=XeP1jNaJtbLZ9tAMNEF5c9JUkUxuC6H9dwrrDT4gNt4,74743
|
587
|
+
sglang/srt/managers/tp_worker.py,sha256=4W7rV7DsAViLygaWwtnQeR29ytfPkq1fnFpr3N1xPJk,11301
|
588
|
+
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=kK0pn8mz-XgLGvVlJK6LvDVp4lnFk5vJH-Cs9NQ5Un4,10959
|
578
589
|
sglang/srt/managers/utils.py,sha256=9_VGE48EK0PXVJ26aYvbRJ6n7gIZALvCcf6uZCccCgM,1369
|
579
|
-
sglang/srt/
|
580
|
-
sglang/srt/mem_cache/
|
581
|
-
sglang/srt/mem_cache/
|
582
|
-
sglang/srt/mem_cache/chunk_cache.py,sha256=MWo4DwRkHKOLKyow53YrGQdvn2dI7hVJuf2Gf-SPAr0,3110
|
590
|
+
sglang/srt/mem_cache/allocator.py,sha256=drpOUu0aNCq-5R0rcQZCxyL8jwt2WFKRU255y2-gaZY,21081
|
591
|
+
sglang/srt/mem_cache/base_prefix_cache.py,sha256=hLS2ncTMAz7Kpdk5pNwn5c6g8b61_K9OCBL4Vj1xsYc,2801
|
592
|
+
sglang/srt/mem_cache/chunk_cache.py,sha256=FU_fq8e_dodgU8EkRqE4Jr0sKwCXQnKmapO88k6_JfU,3207
|
583
593
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
584
|
-
sglang/srt/mem_cache/
|
585
|
-
sglang/srt/mem_cache/
|
586
|
-
sglang/srt/mem_cache/
|
594
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=njuGCGuxO6ry-3Co2r41iRgKWM-J2nkUOD2xsuHwyPk,4968
|
595
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=76uxKFrgOO8yuSygqJhVyMMuPJk4qfpZ285bRoNfgTg,24224
|
596
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=jQdWgOr6hpMLbGaEJc4immBgZG_MZbx8LyOv029ASVw,40932
|
597
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=_FP-M8Cz2cRNQaaRRETM40PfPT1AmqT7DQHMU7cM7-Q,10255
|
587
598
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=wZl2KeEl3xeoEsYdH33UoM-FO8kqfLo_XUgereJVvoM,1348
|
588
|
-
sglang/srt/mem_cache/radix_cache.py,sha256=
|
589
|
-
sglang/srt/
|
599
|
+
sglang/srt/mem_cache/radix_cache.py,sha256=kp4JiVxh3eS4MsFxGKIYjYAb14B777qc1bHrABPqBMc,19101
|
600
|
+
sglang/srt/mem_cache/swa_radix_cache.py,sha256=4qt_gS7GuHiekd6VvKkx54dB2GHJzNA_kj71Np6jTDA,40300
|
601
|
+
sglang/srt/metrics/collector.py,sha256=FH6Wil2lMK7d7q74CfxfdULCaHKDXeAoo8UBZqqdepM,20289
|
590
602
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
591
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
592
|
-
sglang/srt/model_executor/forward_batch_info.py,sha256=
|
593
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
603
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=0f-50fkIBwNiy2gzf_c2ZvmGXtUgWA2GoYONx0MkXgY,30442
|
604
|
+
sglang/srt/model_executor/forward_batch_info.py,sha256=jzhJFe7wTeovC2AgodaNUqH1dkY1ELJoLVcAyn-BjPQ,30290
|
605
|
+
sglang/srt/model_executor/model_runner.py,sha256=oyqHt48lMMK9PBpT0inun1Sh3MOXIPr8ZD2iSwQb8O8,69663
|
594
606
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
595
|
-
sglang/srt/model_loader/loader.py,sha256=
|
596
|
-
sglang/srt/model_loader/utils.py,sha256=
|
607
|
+
sglang/srt/model_loader/loader.py,sha256=wxSUYrqv23w9yHYy9Lm0ozWggs9pf6Co4yqe1UO8PZk,59799
|
608
|
+
sglang/srt/model_loader/utils.py,sha256=svSrPQxViBz_-0_sByu4coCYrzJ51-4FCi_bFqa6rDo,4474
|
597
609
|
sglang/srt/model_loader/weight_utils.py,sha256=dfepjK1lhcFoxX6Vflb3imiHaj9_Tep_uZ7j3lfN9jE,38004
|
598
610
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
599
611
|
sglang/srt/models/bert.py,sha256=ODJe8YfNRP-hHsomFWk4_QpcuiSsNfjzGf256EDS0Pc,15802
|
600
612
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
601
|
-
sglang/srt/models/clip.py,sha256=
|
613
|
+
sglang/srt/models/clip.py,sha256=kOPSXnmgH_QKu2-ENn49HLDS9yf7Gm1HCOE_YvoNhlA,19858
|
602
614
|
sglang/srt/models/commandr.py,sha256=5Y_b3K0QY7D37nFGkyiGgY38RleRui_GJUYcHSuHUZo,15315
|
603
615
|
sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,15598
|
604
|
-
sglang/srt/models/deepseek.py,sha256=
|
605
|
-
sglang/srt/models/deepseek_janus_pro.py,sha256=
|
616
|
+
sglang/srt/models/deepseek.py,sha256=sqobTr9a9c5pNLNJZE-WrJIE_qBq0lC5gCGv9NpGU_Q,17364
|
617
|
+
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
606
618
|
sglang/srt/models/deepseek_nextn.py,sha256=47fehxRdiOizr0rdLg5f1fzQEx6gGAOcDcWKtblloyk,5928
|
607
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
608
|
-
sglang/srt/models/deepseek_vl2.py,sha256=
|
619
|
+
sglang/srt/models/deepseek_v2.py,sha256=g0SUVBZaw4dDK1waGN9fRoJNxnQ9Ughb25MJNQilVPo,104209
|
620
|
+
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
609
621
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
610
|
-
sglang/srt/models/gemma.py,sha256=
|
611
|
-
sglang/srt/models/gemma2.py,sha256=
|
622
|
+
sglang/srt/models/gemma.py,sha256=2atKwFN5wCsJCmBRmURX9vaCcFjxlFirL7xsnG5KPlI,14180
|
623
|
+
sglang/srt/models/gemma2.py,sha256=lpHKN-ovN9IWz3iA9FsR5H86lGatectnM8sjx0GoinM,18033
|
612
624
|
sglang/srt/models/gemma2_reward.py,sha256=V8U3_ADUHWPdOwvEe1jhGW-oJmBgL8t1TY3-67Ksv2A,2618
|
613
|
-
sglang/srt/models/gemma3_causal.py,sha256=
|
614
|
-
sglang/srt/models/gemma3_mm.py,sha256=
|
625
|
+
sglang/srt/models/gemma3_causal.py,sha256=0FdI0wVoJ4ZakBl8ShO29D1uEMO0T8CRjdsfiHzCGY8,27424
|
626
|
+
sglang/srt/models/gemma3_mm.py,sha256=sRvdAOiStlDhC_-sSH226d0awx4ZQJG7Wtdf7PE6ygw,17189
|
615
627
|
sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnLcemC0,36405
|
616
628
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
617
|
-
sglang/srt/models/gemma3n_mm.py,sha256=
|
629
|
+
sglang/srt/models/gemma3n_mm.py,sha256=pL_fvnkz9fKaC2Afms5KG3Me3u5sp1C2-mAUhqPGrQ4,18701
|
618
630
|
sglang/srt/models/glm4.py,sha256=2VQzUqFkQTy_2nfkxP9SF6_9kKLTZUExGRjge7r99Es,11265
|
619
631
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
620
632
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
621
633
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
622
|
-
sglang/srt/models/
|
623
|
-
sglang/srt/models/
|
634
|
+
sglang/srt/models/granitemoe.py,sha256=diq5Xp_jg0RX5629iAu7eeTYPYOxfg95-FoKUQwt2Ic,13723
|
635
|
+
sglang/srt/models/grok.py,sha256=wY3flIJdr00wYvW-_PHXrXwh-R7vlTnf1UKhjPN8Egc,28199
|
636
|
+
sglang/srt/models/hunyuan.py,sha256=GVDeMKgcqW6HMFWPUukznL5JoDW4CpOpS5Q_PXlbHw8,31071
|
624
637
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
625
638
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
626
639
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
627
|
-
sglang/srt/models/internvl.py,sha256=
|
628
|
-
sglang/srt/models/kimi_vl.py,sha256=
|
640
|
+
sglang/srt/models/internvl.py,sha256=OeQy0wCXBdqXB98cx9TNJ64K2YdT0AVIX_1xVYa-Jbg,23333
|
641
|
+
sglang/srt/models/kimi_vl.py,sha256=XulRiufQzOSWZe8-bUl2OEdznvsVU9OBsEYipaX3YkM,12877
|
629
642
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
630
|
-
sglang/srt/models/llama.py,sha256=
|
631
|
-
sglang/srt/models/llama4.py,sha256=
|
643
|
+
sglang/srt/models/llama.py,sha256=Nsxv2s1sOmLnZsTHkwbTh53cUFEQ2fnKDQi5BFbFcsk,28994
|
644
|
+
sglang/srt/models/llama4.py,sha256=J8zuYOrQ8iV7CyWuLdjFmOyi7eD4GA7iqiaoKzGO-N8,18797
|
632
645
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
633
646
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
634
647
|
sglang/srt/models/llama_eagle3.py,sha256=715soylDE3kOMWskbPy_70BFxaSc5ptaHCS1v3-ViA0,8579
|
635
648
|
sglang/srt/models/llama_embedding.py,sha256=zq-_lNu35VBFc7eemiam0zdkGIE8fzrgk5OWYfirZnA,3254
|
636
649
|
sglang/srt/models/llama_reward.py,sha256=LF2nqMV5XOrljGjAwJg43mBv3z6Q040I2EYlgZeCp8k,4681
|
637
|
-
sglang/srt/models/llava.py,sha256=
|
638
|
-
sglang/srt/models/llavavid.py,sha256
|
650
|
+
sglang/srt/models/llava.py,sha256=_UBDz_S8AObV39w0XWkCPNQTxHMc27KH9PJHz98kzx4,37541
|
651
|
+
sglang/srt/models/llavavid.py,sha256=-CSk0RJ2MQeb81sh-RISeVJFaI-XWY6nR6_I594MkME,12818
|
639
652
|
sglang/srt/models/mimo.py,sha256=Mp-iFp4YHuiuq-H8enUF5K5QbMnVcvEa6mURH6vM3yM,6140
|
640
653
|
sglang/srt/models/mimo_mtp.py,sha256=jSmqJAXu7G3OO7jW1oa2suI4H_Yl7u5ZT7w4lHFbHhg,7292
|
641
|
-
sglang/srt/models/minicpm.py,sha256=
|
654
|
+
sglang/srt/models/minicpm.py,sha256=CzBJyZtfMpp8jvlEl29DHI7HLVq-CxuqP1UHwxIbaUI,14567
|
642
655
|
sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE,19347
|
643
|
-
sglang/srt/models/minicpmo.py,sha256=
|
644
|
-
sglang/srt/models/minicpmv.py,sha256=
|
645
|
-
sglang/srt/models/mistral.py,sha256=
|
646
|
-
sglang/srt/models/mixtral.py,sha256=
|
656
|
+
sglang/srt/models/minicpmo.py,sha256=urYHq2sVgvswZtDA_pYFa4HWJv17rspn-DajmfgDr_Y,75868
|
657
|
+
sglang/srt/models/minicpmv.py,sha256=g4aAOG8PVGkZqGmlneVaScAtNpSLqSVbZGRAikyrBy8,30394
|
658
|
+
sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,3475
|
659
|
+
sglang/srt/models/mixtral.py,sha256=j2whKt4GdQqtpKL5iN0Vb4TO4el1E2qEpUCI57E_47Q,17222
|
647
660
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
648
|
-
sglang/srt/models/mllama.py,sha256=
|
649
|
-
sglang/srt/models/mllama4.py,sha256=
|
661
|
+
sglang/srt/models/mllama.py,sha256=OdX7brhyfGiMFPulxF77QOUi-Kcscg3Qo4ipyxzs9yA,39670
|
662
|
+
sglang/srt/models/mllama4.py,sha256=JsVrvDeWHwPemefvLMU8OWqm8uEQqE-n2CaOk8zoOQw,20237
|
650
663
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
651
664
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
652
|
-
sglang/srt/models/olmoe.py,sha256=
|
665
|
+
sglang/srt/models/olmoe.py,sha256=WdPtyKsd3u8OpVsXmDwWuVpt1gTF0679IRkc1pvfnMM,16040
|
666
|
+
sglang/srt/models/persimmon.py,sha256=86Duo3HiZqDj9O2UzWbJgUEhQOXzGBUdhUofQhcs1VE,11244
|
667
|
+
sglang/srt/models/phi.py,sha256=n6A1d47MvnR1lmSsZ3TuzXk5kT1Lntj_YQ5uNvR0s5o,10287
|
653
668
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
654
|
-
sglang/srt/models/phi4mm.py,sha256=
|
655
|
-
sglang/srt/models/
|
669
|
+
sglang/srt/models/phi4mm.py,sha256=Yh2GnrT8zyvOTMPslHbhUlNOTAzZ6LuzMNxKaJjr38c,21107
|
670
|
+
sglang/srt/models/phi4mm_audio.py,sha256=0ChekwoYudAnbY0-JyNwz_inzMlxM8FmULqR9mwkPhQ,48877
|
671
|
+
sglang/srt/models/phi4mm_utils.py,sha256=bW3un4x3SHDvSkAOHQEFO286FGdOPeKhBpJCOmNlC9E,66956
|
672
|
+
sglang/srt/models/phimoe.py,sha256=RZzcNf3sunyoc0KyMpyd93gnn1Ni13bqO-xe00MJ-h0,19192
|
656
673
|
sglang/srt/models/pixtral.py,sha256=ZkZrV0mEfmbBdgRko2AvsMFZbAVskgp_5a5p1xCSRN0,16835
|
657
|
-
sglang/srt/models/qwen.py,sha256=
|
658
|
-
sglang/srt/models/qwen2.py,sha256=
|
659
|
-
sglang/srt/models/qwen2_5_vl.py,sha256=
|
660
|
-
sglang/srt/models/qwen2_audio.py,sha256=
|
674
|
+
sglang/srt/models/qwen.py,sha256=j0OU3JjznWi_TbayI09yYGM-Obov6mQzJO82Hs0qBGw,11868
|
675
|
+
sglang/srt/models/qwen2.py,sha256=0gnggs2q-_FtD75J-UM4KMNBXSapVQGz73B-C2yZHDg,22437
|
676
|
+
sglang/srt/models/qwen2_5_vl.py,sha256=vOuIyK_NLuGgz9LlAdyM7cSQUU93VnBCYXUr_n4iOLs,22708
|
677
|
+
sglang/srt/models/qwen2_audio.py,sha256=lVeYmC29eVZIR9I6ZjFe4xvC0wSXR0NtGCli6fSXtms,7870
|
661
678
|
sglang/srt/models/qwen2_classification.py,sha256=dGrMm4ebd30_lBhHOhaV57ig2iOTx3nqB4GEzsrRIM8,2747
|
662
679
|
sglang/srt/models/qwen2_eagle.py,sha256=6spFg6JYQGeUXLv2Q5eMkVzZvnqGyvW6SdVBtFMxlTM,4806
|
663
|
-
sglang/srt/models/qwen2_moe.py,sha256=
|
680
|
+
sglang/srt/models/qwen2_moe.py,sha256=FjR9y0w4kcDi8rZ3I8ai-2jf5osDUVNYYaSUKXKkjzs,25897
|
664
681
|
sglang/srt/models/qwen2_rm.py,sha256=-mQXDEv11p-I1HXgYLTtY6ROem6UYorO958WsDrzsgs,2837
|
665
|
-
sglang/srt/models/qwen2_vl.py,sha256=
|
666
|
-
sglang/srt/models/qwen3.py,sha256=
|
667
|
-
sglang/srt/models/qwen3_moe.py,sha256=
|
682
|
+
sglang/srt/models/qwen2_vl.py,sha256=ZRAL32Ymt4ZCBqB0JorXAm4ZBrECZ9EbaXKaTSikkQM,21366
|
683
|
+
sglang/srt/models/qwen3.py,sha256=COSC1TsCQNTq3E1QoVJYj1yTn-CFEVEX7keRwrrBXLs,20121
|
684
|
+
sglang/srt/models/qwen3_moe.py,sha256=TbH1Y2-IcDhef5qjEogF1YXmTv2wsETQVuUytrO7eQo,34080
|
668
685
|
sglang/srt/models/registry.py,sha256=bH9H0OiNV0Cn7FRBM30Oh6dxICTs9mJscdLtHYPJvxc,3783
|
669
686
|
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
670
687
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
671
688
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
672
689
|
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
673
690
|
sglang/srt/models/transformers.py,sha256=_CL0npi-_HvqzxkLgFhv2EE3bfGvCLXPYAtPFywZOr0,10260
|
674
|
-
sglang/srt/models/vila.py,sha256=
|
691
|
+
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
675
692
|
sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,14035
|
676
693
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
677
694
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
678
695
|
sglang/srt/multimodal/mm_utils.py,sha256=6bV1_a7Iet9W0y3qdd0E-hFM78zalIzNZCYbLzJX2y8,12640
|
679
|
-
sglang/srt/multimodal/processors/base_processor.py,sha256=
|
680
|
-
sglang/srt/multimodal/processors/clip.py,sha256=
|
681
|
-
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=
|
682
|
-
sglang/srt/multimodal/processors/gemma3.py,sha256=
|
683
|
-
sglang/srt/multimodal/processors/gemma3n.py,sha256=
|
684
|
-
sglang/srt/multimodal/processors/internvl.py,sha256=
|
685
|
-
sglang/srt/multimodal/processors/janus_pro.py,sha256=
|
686
|
-
sglang/srt/multimodal/processors/kimi_vl.py,sha256=
|
687
|
-
sglang/srt/multimodal/processors/llava.py,sha256=
|
688
|
-
sglang/srt/multimodal/processors/minicpm.py,sha256=
|
689
|
-
sglang/srt/multimodal/processors/mlama.py,sha256=
|
690
|
-
sglang/srt/multimodal/processors/mllama4.py,sha256=
|
691
|
-
sglang/srt/multimodal/processors/phi4mm.py,sha256=
|
692
|
-
sglang/srt/multimodal/processors/pixtral.py,sha256=
|
693
|
-
sglang/srt/multimodal/processors/
|
694
|
-
sglang/srt/multimodal/processors/
|
696
|
+
sglang/srt/multimodal/processors/base_processor.py,sha256=ZkMeNej7Mdlhu61DEcDCs7gcM8zUntzF_J4V_Q6yZ6c,23780
|
697
|
+
sglang/srt/multimodal/processors/clip.py,sha256=bpFaqQqNtjAriO-Do8pIYgYOwUh09JLC7cA4lx6X2Bs,1023
|
698
|
+
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=sdObVNZKXzlWlsuUKTR-NWdoAZHEHBTGCtOGfusNM5o,2535
|
699
|
+
sglang/srt/multimodal/processors/gemma3.py,sha256=wLLe6VnNs7CSW8uT2Gj0dPwszFXf2yRpY14GYNfFDq4,1952
|
700
|
+
sglang/srt/multimodal/processors/gemma3n.py,sha256=KHH3wp6zoCnlKiAh1wWn7ffvTqeT_ZuQZrBaayBHVsQ,3022
|
701
|
+
sglang/srt/multimodal/processors/internvl.py,sha256=wNXjIEyp3t4ls5GozRhUXebKClL1YXh5U52YK3H1TIE,9280
|
702
|
+
sglang/srt/multimodal/processors/janus_pro.py,sha256=bcsSBAS8joLQFtnRQ1b6SrQnVABVBNCXTkTPkmSgssA,1437
|
703
|
+
sglang/srt/multimodal/processors/kimi_vl.py,sha256=RKNOKZhEAqjeB-CWdgWjHHxtawsNR1WPHfYaEfCVkko,1531
|
704
|
+
sglang/srt/multimodal/processors/llava.py,sha256=3XnpfYdvW4GlO7NU0sBqwTd6zgSsn5fBndWcmsPgGXs,8029
|
705
|
+
sglang/srt/multimodal/processors/minicpm.py,sha256=uTfEjK1hdiGiZ-y4oEPByUP96omDQwnCbaWEWw-Acr4,5321
|
706
|
+
sglang/srt/multimodal/processors/mlama.py,sha256=l8_LG5_gLENAu92bKzNCzkA38b6tHv1oVoSpQWFJPv8,1199
|
707
|
+
sglang/srt/multimodal/processors/mllama4.py,sha256=N9Occ3NslKSQT4i8VaL-3mnkMrFAWTQad6cUArYHdoI,5573
|
708
|
+
sglang/srt/multimodal/processors/phi4mm.py,sha256=xZ7YYyVHdQ-bovh1SWLidZddxXV6Iw1Nz1yNt_li3I4,3823
|
709
|
+
sglang/srt/multimodal/processors/pixtral.py,sha256=RuLd5PTTPQSJ1tZT2YelW0-jx6P79wkZBWvCUz98VLM,3169
|
710
|
+
sglang/srt/multimodal/processors/qwen_audio.py,sha256=ILePOlBI5v8GI962q-pZ0dV-tkHrfpKeL81dWHeuO70,2333
|
711
|
+
sglang/srt/multimodal/processors/qwen_vl.py,sha256=6maMXOwX3QICy3YNVSAF4VwxrZHCT4XH0MAAXIwIaeM,10464
|
712
|
+
sglang/srt/multimodal/processors/vila.py,sha256=Dj66JpKbSdqpLNfk-NykYjhGAGuzBeMo7lFVCkeHkAM,2142
|
695
713
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
696
714
|
sglang/srt/sampling/sampling_batch_info.py,sha256=m8m-mXu3N8hLYFhAkRopePDT5Ozkd4KAmWDgM_9_4iA,14536
|
697
|
-
sglang/srt/sampling/sampling_params.py,sha256=
|
715
|
+
sglang/srt/sampling/sampling_params.py,sha256=HbVcCeSXgPW19MRB-v0FTG1D-zHDAY6-toxyndSl-zI,6462
|
698
716
|
sglang/srt/sampling/penaltylib/__init__.py,sha256=mtN8grFEcaBUhl4yBHmw8NNirt_i6uKO2cDNLHOpZQE,496
|
699
717
|
sglang/srt/sampling/penaltylib/frequency_penalty.py,sha256=Loc3qjJTksNc5s-DV7QZHjgqoo5pxk7-nZzxwyhD2tQ,2144
|
700
718
|
sglang/srt/sampling/penaltylib/min_new_tokens.py,sha256=rdU_D7RoIcrQPhysNQEzmr4TO2OoEi___p-i3QdwkgU,3331
|
@@ -702,7 +720,7 @@ sglang/srt/sampling/penaltylib/orchestrator.py,sha256=XM-Lm6u7gYPtMZrTIc0FR4QxNZ
|
|
702
720
|
sglang/srt/sampling/penaltylib/presence_penalty.py,sha256=NRh10AJrrQlGJ6S-enGdRefrTrWpyqrSm-aNnyqQNQQ,2119
|
703
721
|
sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18nst2oOD8HnA2mZ4,12859
|
704
722
|
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=fSNaHYJOQUgy2_AHRlZPYSQRIMgSiL_Pz5h53eothx4,14239
|
705
|
-
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=
|
723
|
+
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=LBAvhZ1ZUC-TSOQ45wG2GzBAc3kvSEdg5xKXS-xkBUc,15309
|
706
724
|
sglang/srt/speculative/eagle_utils.py,sha256=cBQYqryCr4is5E_16xIcUue0Q2_Mn4meY8NCyuu4RAg,45558
|
707
725
|
sglang/srt/speculative/eagle_worker.py,sha256=iOwloJqhYIrgBdnZQz9NV3zuiAe5dXJJa0QeSIg92x8,38180
|
708
726
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
@@ -710,7 +728,7 @@ sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
710
728
|
sglang/test/few_shot_gsm8k.py,sha256=qnEejCyPHGEMBEiNc7T4-t9lvoo2DNN72RXw-ei_TnY,4300
|
711
729
|
sglang/test/few_shot_gsm8k_engine.py,sha256=Yf1Dg0Tk-tY4v1oj_UTxJ7950CWn6kRMbQKDjT2Orgo,3902
|
712
730
|
sglang/test/run_eval.py,sha256=K4Z3OdMPvLeuGJhWWTBD0F-MOUFeBYLvsPnDQ44bd18,4036
|
713
|
-
sglang/test/runners.py,sha256=
|
731
|
+
sglang/test/runners.py,sha256=kRperGVKBW6pS05iOqZ1plSaWb4lX3tmHQOnPRd137c,33473
|
714
732
|
sglang/test/send_one.py,sha256=XNZdfZs21tXDBwrDj2pq46WQd5smiKoYETY8U09c1Z8,5079
|
715
733
|
sglang/test/simple_eval_common.py,sha256=OW4Z7O33QqDySRFuHIC4Ouidfup4eaOEuR9i7xJzkDY,12379
|
716
734
|
sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
|
@@ -719,24 +737,26 @@ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWU
|
|
719
737
|
sglang/test/simple_eval_mgsm.py,sha256=rd7TSUyxdKbrXaVoewo24V8lCo_6kO8zxPhhmvylpw8,10259
|
720
738
|
sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
|
721
739
|
sglang/test/test_activation.py,sha256=GeTIJHxlLQfW3kM-X1FGa8Sa3dSGKHEXl5wEy-hfGis,1489
|
722
|
-
sglang/test/test_block_fp8.py,sha256=
|
740
|
+
sglang/test/test_block_fp8.py,sha256=hd3GXuC_wxn0HGAN3KCs6Nxf98AHO8XaRvGsvWS-CHc,21822
|
723
741
|
sglang/test/test_block_fp8_deep_gemm_blackwell.py,sha256=Hnhq4kkyINHb4ONedkp5Kf7Xx0MjOoOBYL8J7ETvOVA,8180
|
724
|
-
sglang/test/test_block_fp8_ep.py,sha256=
|
725
|
-
sglang/test/test_custom_ops.py,sha256=
|
742
|
+
sglang/test/test_block_fp8_ep.py,sha256=XGZEs7cJiLjatRZcdcav4aFIQxnQB8Vq-b3HmAsw-Ww,10859
|
743
|
+
sglang/test/test_custom_ops.py,sha256=PenQ8zM1wj5xwiVEPVzD37pO-x90aOfFMpCRZenaKsY,5709
|
726
744
|
sglang/test/test_cutlass_moe.py,sha256=beXdvpwpHh0O8fpLW-RV3Bx8Wu0lRFG_SNkL3Op5ITA,9905
|
727
|
-
sglang/test/test_cutlass_w4a8_moe.py,sha256=
|
745
|
+
sglang/test/test_cutlass_w4a8_moe.py,sha256=u4Fk2Kdu5yodhsPuiwTIJlWCpWgW5vMBmd1EDwdkDXw,8724
|
728
746
|
sglang/test/test_deepep_utils.py,sha256=749ysTBGNzh6rYUCJhhZBtZpeD15eWTeNHYCytcvZtc,7448
|
729
747
|
sglang/test/test_dynamic_grad_mode.py,sha256=L76yUCuk_ymNpXD2CmO8r2GiGjIvD_gtTsuFDs2NolI,1638
|
730
|
-
sglang/test/test_fp4_moe.py,sha256=
|
748
|
+
sglang/test/test_fp4_moe.py,sha256=yOYpn1dAztaRMBQYzsxU8222HZe2V_tg0Pz_gy9PNY0,8131
|
731
749
|
sglang/test/test_layernorm.py,sha256=2GMWqqNDuGvSMSsEBF5eDCzwVSYA9E6hGhRo6s4ecKg,3764
|
750
|
+
sglang/test/test_marlin_moe.py,sha256=PITMGcGF4ci2csXJejdLSNuxpURnFmcflsipAZsGakU,7991
|
751
|
+
sglang/test/test_marlin_utils.py,sha256=gFMJwxbfEEJDeHI-HU5FDF9FFqqcM-yahK0TWyVIVgQ,5171
|
732
752
|
sglang/test/test_programs.py,sha256=DJIbTChloPwaDiEWHQoSTuKv3BGx0-K8Y5e1mDDTACM,18910
|
733
|
-
sglang/test/test_utils.py,sha256=
|
753
|
+
sglang/test/test_utils.py,sha256=dnn2PUNoN4VX6glRlx3MmtTIqkoz3eisYa9VOYNfodU,37840
|
734
754
|
sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
735
755
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
736
756
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
737
757
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
738
|
-
sglang-0.4.9.
|
739
|
-
sglang-0.4.9.
|
740
|
-
sglang-0.4.9.
|
741
|
-
sglang-0.4.9.
|
742
|
-
sglang-0.4.9.
|
758
|
+
sglang-0.4.9.post3.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
759
|
+
sglang-0.4.9.post3.dist-info/METADATA,sha256=QMSrhtk8BvwA8a_1DH3S77Yvhh6NCVv-KCef3au0MIE,27353
|
760
|
+
sglang-0.4.9.post3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
761
|
+
sglang-0.4.9.post3.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
762
|
+
sglang-0.4.9.post3.dist-info/RECORD,,
|