sglang 0.4.9.post6__py3-none-any.whl → 0.4.10.post1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- sglang/bench_offline_throughput.py +20 -0
- sglang/bench_one_batch.py +3 -0
- sglang/srt/configs/__init__.py +8 -0
- sglang/srt/configs/model_config.py +4 -0
- sglang/srt/configs/step3_vl.py +172 -0
- sglang/srt/conversation.py +23 -0
- sglang/srt/disaggregation/decode.py +2 -8
- sglang/srt/disaggregation/launch_lb.py +5 -20
- sglang/srt/disaggregation/mooncake/conn.py +33 -15
- sglang/srt/disaggregation/prefill.py +2 -6
- sglang/srt/distributed/parallel_state.py +86 -1
- sglang/srt/entrypoints/engine.py +14 -18
- sglang/srt/entrypoints/http_server.py +10 -2
- sglang/srt/entrypoints/openai/serving_chat.py +2 -21
- sglang/srt/eplb/expert_distribution.py +5 -0
- sglang/srt/eplb/expert_location.py +17 -6
- sglang/srt/eplb/expert_location_dispatch.py +1 -0
- sglang/srt/eplb/expert_location_updater.py +2 -0
- sglang/srt/function_call/function_call_parser.py +2 -0
- sglang/srt/function_call/step3_detector.py +436 -0
- sglang/srt/hf_transformers_utils.py +2 -0
- sglang/srt/jinja_template_utils.py +4 -1
- sglang/srt/layers/attention/trtllm_mla_backend.py +372 -0
- sglang/srt/layers/attention/utils.py +6 -1
- sglang/srt/layers/moe/cutlass_moe.py +2 -1
- sglang/srt/layers/moe/ep_moe/layer.py +39 -674
- sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +26 -13
- sglang/srt/layers/moe/fused_moe_triton/layer.py +152 -39
- sglang/srt/layers/quantization/fp8.py +52 -18
- sglang/srt/layers/quantization/unquant.py +0 -8
- sglang/srt/layers/quantization/w4afp8.py +1 -0
- sglang/srt/layers/quantization/w8a8_int8.py +4 -1
- sglang/srt/managers/cache_controller.py +165 -67
- sglang/srt/managers/data_parallel_controller.py +2 -0
- sglang/srt/managers/io_struct.py +0 -2
- sglang/srt/managers/scheduler.py +90 -671
- sglang/srt/managers/scheduler_metrics_mixin.py +229 -0
- sglang/srt/managers/scheduler_profiler_mixin.py +279 -0
- sglang/srt/managers/scheduler_update_weights_mixin.py +142 -0
- sglang/srt/managers/template_manager.py +62 -19
- sglang/srt/managers/tokenizer_manager.py +123 -74
- sglang/srt/managers/tp_worker.py +4 -0
- sglang/srt/managers/tp_worker_overlap_thread.py +2 -1
- sglang/srt/mem_cache/hicache_storage.py +60 -17
- sglang/srt/mem_cache/hiradix_cache.py +36 -8
- sglang/srt/mem_cache/memory_pool.py +15 -118
- sglang/srt/mem_cache/memory_pool_host.py +418 -29
- sglang/srt/mem_cache/mooncake_store/mooncake_store.py +264 -0
- sglang/srt/mem_cache/mooncake_store/unit_test.py +40 -0
- sglang/srt/mem_cache/nixl/hicache_nixl.py +163 -0
- sglang/srt/mem_cache/nixl/nixl_utils.py +238 -0
- sglang/srt/mem_cache/nixl/test_hicache_nixl_storage.py +216 -0
- sglang/srt/mem_cache/storage/hf3fs/client_hf3fs.py +183 -0
- sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +278 -0
- sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py +43 -0
- sglang/srt/model_executor/cuda_graph_runner.py +25 -1
- sglang/srt/model_executor/model_runner.py +13 -1
- sglang/srt/model_loader/weight_utils.py +2 -0
- sglang/srt/models/arcee.py +532 -0
- sglang/srt/models/deepseek_v2.py +7 -6
- sglang/srt/models/glm4_moe.py +6 -4
- sglang/srt/models/granitemoe.py +3 -0
- sglang/srt/models/grok.py +3 -0
- sglang/srt/models/hunyuan.py +1 -0
- sglang/srt/models/llama4.py +3 -0
- sglang/srt/models/mixtral.py +3 -0
- sglang/srt/models/olmoe.py +3 -0
- sglang/srt/models/phimoe.py +1 -0
- sglang/srt/models/step3_vl.py +991 -0
- sglang/srt/multimodal/processors/base_processor.py +15 -16
- sglang/srt/multimodal/processors/step3_vl.py +515 -0
- sglang/srt/reasoning_parser.py +2 -1
- sglang/srt/server_args.py +49 -18
- sglang/srt/speculative/eagle_worker.py +2 -0
- sglang/srt/utils.py +1 -0
- sglang/test/attention/test_trtllm_mla_backend.py +945 -0
- sglang/utils.py +0 -11
- sglang/version.py +1 -1
- {sglang-0.4.9.post6.dist-info → sglang-0.4.10.post1.dist-info}/METADATA +3 -4
- {sglang-0.4.9.post6.dist-info → sglang-0.4.10.post1.dist-info}/RECORD +83 -65
- {sglang-0.4.9.post6.dist-info → sglang-0.4.10.post1.dist-info}/WHEEL +0 -0
- {sglang-0.4.9.post6.dist-info → sglang-0.4.10.post1.dist-info}/licenses/LICENSE +0 -0
- {sglang-0.4.9.post6.dist-info → sglang-0.4.10.post1.dist-info}/top_level.txt +0 -0
sglang/utils.py
CHANGED
@@ -291,17 +291,6 @@ def find_printable_text(text: str):
|
|
291
291
|
return text[: text.rfind(" ") + 1]
|
292
292
|
|
293
293
|
|
294
|
-
def graceful_registry(sub_module_name: str):
|
295
|
-
def graceful_shutdown(signum, frame):
|
296
|
-
logger.info(
|
297
|
-
f"{sub_module_name} Received signal to shutdown. Performing graceful shutdown..."
|
298
|
-
)
|
299
|
-
if signum == signal.SIGTERM:
|
300
|
-
logger.info(f"{sub_module_name} receive sigterm")
|
301
|
-
|
302
|
-
signal.signal(signal.SIGTERM, graceful_shutdown)
|
303
|
-
|
304
|
-
|
305
294
|
class LazyImport:
|
306
295
|
"""Lazy import to make `import sglang` run faster."""
|
307
296
|
|
sglang/version.py
CHANGED
@@ -1 +1 @@
|
|
1
|
-
__version__ = "0.4.
|
1
|
+
__version__ = "0.4.10.post1"
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: sglang
|
3
|
-
Version: 0.4.
|
3
|
+
Version: 0.4.10.post1
|
4
4
|
Summary: SGLang is yet another fast serving framework for large language models and vision language models.
|
5
5
|
License: Apache License
|
6
6
|
Version 2.0, January 2004
|
@@ -246,14 +246,14 @@ Requires-Dist: sentencepiece; extra == "runtime-common"
|
|
246
246
|
Requires-Dist: soundfile==0.13.1; extra == "runtime-common"
|
247
247
|
Requires-Dist: scipy; extra == "runtime-common"
|
248
248
|
Requires-Dist: torchao==0.9.0; extra == "runtime-common"
|
249
|
-
Requires-Dist: transformers==4.54.
|
249
|
+
Requires-Dist: transformers==4.54.1; extra == "runtime-common"
|
250
250
|
Requires-Dist: timm==1.0.16; extra == "runtime-common"
|
251
251
|
Requires-Dist: uvicorn; extra == "runtime-common"
|
252
252
|
Requires-Dist: uvloop; extra == "runtime-common"
|
253
253
|
Requires-Dist: xgrammar==0.1.21; extra == "runtime-common"
|
254
254
|
Provides-Extra: srt
|
255
255
|
Requires-Dist: sglang[runtime_common]; extra == "srt"
|
256
|
-
Requires-Dist: sgl-kernel==0.2.
|
256
|
+
Requires-Dist: sgl-kernel==0.2.8; extra == "srt"
|
257
257
|
Requires-Dist: torch==2.7.1; extra == "srt"
|
258
258
|
Requires-Dist: torchaudio==2.7.1; extra == "srt"
|
259
259
|
Requires-Dist: torchvision==0.22.1; extra == "srt"
|
@@ -427,7 +427,6 @@ SGLang has been deployed at large scale, generating trillions of tokens in produ
|
|
427
427
|
<img src="https://raw.githubusercontent.com/sgl-project/sgl-learning-materials/refs/heads/main/slides/adoption.png" alt="logo" width="800" margin="10px"></img>
|
428
428
|
|
429
429
|
## Contact Us
|
430
|
-
|
431
430
|
For enterprises interested in adopting or deploying SGLang at scale, including technical consulting, sponsorship opportunities, or partnership inquiries, please contact us at contact@sglang.ai.
|
432
431
|
|
433
432
|
## Acknowledgment
|
@@ -1,7 +1,7 @@
|
|
1
1
|
sglang/__init__.py,sha256=x1v8748WXS2BAptWAd5fR3YBEkngC7e_P_rkCNuNCGg,1702
|
2
2
|
sglang/api.py,sha256=rcp3GeoyZhmJ0GDLPRkuZNcxd0TBJy_wfUDpcmQoqW8,7210
|
3
|
-
sglang/bench_offline_throughput.py,sha256=
|
4
|
-
sglang/bench_one_batch.py,sha256=
|
3
|
+
sglang/bench_offline_throughput.py,sha256=Bge0KG4Uiv9CHsxDnqKdXJmG_TcxM4blz3CmvLmDRvM,14815
|
4
|
+
sglang/bench_one_batch.py,sha256=kSqUxn8kEib6GkEdSDZgAaY6P1JuFL2BadbfVuXJjQs,19610
|
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
|
@@ -9,8 +9,8 @@ sglang/compile_deep_gemm.py,sha256=H118s76CKdpZr-cDeFfBCePe7--c_teEBNVIzchYVSo,6
|
|
9
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
|
-
sglang/utils.py,sha256=
|
13
|
-
sglang/version.py,sha256=
|
12
|
+
sglang/utils.py,sha256=C_r3OF-OA6DwUz6KYQF6xWUBApjHaqSPsV9JccafrWI,16403
|
13
|
+
sglang/version.py,sha256=UbzK-YnSSFDgJG6Hobrf-GLxjV7dEUOjLLPQZxNXD3E,29
|
14
14
|
sglang/eval/llama3_eval.py,sha256=gWSboDchIGybIce88bJlrCG0yiLZ513mw4gcutJlzGM,10017
|
15
15
|
sglang/eval/loogle_eval.py,sha256=-CC2s2kh5qUoDrHRkQVkC_jNvBgNojXbf456ny5s78s,4557
|
16
16
|
sglang/lang/chat_template.py,sha256=ZNcuDvDZE9781tQqfKpptck_zJVK0aggq7IxrNHltao,21934
|
@@ -30,22 +30,22 @@ sglang/srt/_custom_ops.py,sha256=9GPNUyqnybgvUnzdQ8n5_NgluHmQNw0Gptos0iLPfrY,534
|
|
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=
|
33
|
+
sglang/srt/conversation.py,sha256=31MIxTupi-8sEivQeT3tgv1e90rdQ0VWrmaqytSbqgY,42234
|
34
34
|
sglang/srt/custom_op.py,sha256=7OPQAZe3PqDXk-xM0Wxl7pm9cazilNJfkNiYIWztWgI,3198
|
35
|
-
sglang/srt/hf_transformers_utils.py,sha256
|
36
|
-
sglang/srt/jinja_template_utils.py,sha256=
|
35
|
+
sglang/srt/hf_transformers_utils.py,sha256=-BIA9hykEQIFMnlRVskgi46jJMlW5HFo8CBEqX0-BvI,12455
|
36
|
+
sglang/srt/jinja_template_utils.py,sha256=LHqdxzuYfUbRY-QV8tYYPejulf1RrxNy--M3JFLKEZU,7255
|
37
37
|
sglang/srt/model_parallel.py,sha256=eLXZhvJ4wG6dh0FontNCIdVZvHYdWgaeY-5cu7TD9tE,6078
|
38
38
|
sglang/srt/operations.py,sha256=ddQ8KO63L73OciaR8MZ9h2h83gKVY4-WuWgeEGowPJA,5346
|
39
39
|
sglang/srt/operations_strategy.py,sha256=Pwd2sKeRtKh9WJXgzlNr2tU9y6YMcI3MDLbatHqlMws,7145
|
40
40
|
sglang/srt/patch_torch.py,sha256=OUPCGQSQz3MVZB1zZ_Eq8lXiw0uIKJ_HWjqQolI8FsM,3088
|
41
41
|
sglang/srt/poll_based_barrier.py,sha256=9vjn32ROlSueEk7EuZjWKUrrL7XVR9KJsSVliGTYB_4,937
|
42
|
-
sglang/srt/reasoning_parser.py,sha256=
|
43
|
-
sglang/srt/server_args.py,sha256
|
42
|
+
sglang/srt/reasoning_parser.py,sha256=pN7SbLjaiyT5tdrAZgOFWy3QrDKnZEHkBFeIKFXknZM,9288
|
43
|
+
sglang/srt/server_args.py,sha256=0L6rOyOSlGzScn3L_ifLNNLmzcYQZmKBfCL4AMqwQHw,87628
|
44
44
|
sglang/srt/torch_memory_saver_adapter.py,sha256=K_eTx0UU84MHSTXI3iqYLdHV4IWtJMJ2FKdGFJR8v1E,2417
|
45
45
|
sglang/srt/two_batch_overlap.py,sha256=AgaPeAXJQjt4RVhIVKR2YMEZRL8NqjN93NpgDE_fXfQ,28892
|
46
|
-
sglang/srt/utils.py,sha256=
|
46
|
+
sglang/srt/utils.py,sha256=qpwCJ9_JNgviPSiuCmX4n2FCNxkiAKFTqf1l2BRvmOo,93364
|
47
47
|
sglang/srt/warmup.py,sha256=zldxhMlXpclRAJXmfBjJNUJd1eDizVdysibBvQyTVuA,1782
|
48
|
-
sglang/srt/configs/__init__.py,sha256=
|
48
|
+
sglang/srt/configs/__init__.py,sha256=gas3cKYVgZp7qF4m8FejX4EUUmdQd_w5WDTm7fo7yM0,743
|
49
49
|
sglang/srt/configs/chatglm.py,sha256=j-b0YkdYUmQm2y1kNmMJtKeACxWKmBbvNNkDWbs6kbI,2907
|
50
50
|
sglang/srt/configs/dbrx.py,sha256=tdhIkXAQl1yr0MxqFmsDG1E0e2puRTTKm6UTyANBLac,11005
|
51
51
|
sglang/srt/configs/deepseekvl2.py,sha256=sYMmoy5_LlDXht7MTi4QGYOaiE8iMGUO44bnuOu4i8I,23683
|
@@ -56,7 +56,8 @@ sglang/srt/configs/janus_pro.py,sha256=yI2c_aWBIKiTcK6RZxK6hq8CIxyYRH_NN8uaSNKsr
|
|
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=
|
59
|
+
sglang/srt/configs/model_config.py,sha256=opeGqkpJcCjPLNLSa_Wf2PfQPB17leJKYO_VgYi17q8,28888
|
60
|
+
sglang/srt/configs/step3_vl.py,sha256=_Otgnym57DVgB_kZ__8c1_Ys5gSalA_K0ZuVjcG51T0,4845
|
60
61
|
sglang/srt/configs/update_config.py,sha256=D-myV9Ombwp6wTF0RX9qUO6m5rxFiUcyse32FQADG28,4787
|
61
62
|
sglang/srt/configs/utils.py,sha256=3nHUfisMs_Ltuhv8OZTNCJp63YJKJVF43h1QZB1zqx8,670
|
62
63
|
sglang/srt/connector/__init__.py,sha256=czLX5JOxuMhH-T9eSJzoc1qv1B4z9chyffDRL5I6wo4,1247
|
@@ -78,12 +79,12 @@ sglang/srt/debug_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3
|
|
78
79
|
sglang/srt/debug_utils/dump_comparator.py,sha256=8ZPwP0zojfRHvPiSKgpESYFcC3tR-sBjIej5SotOmpg,3947
|
79
80
|
sglang/srt/debug_utils/dumper.py,sha256=eyrg5lmwyYF88kn8b06kpu1__aGnWb6CLM8fxywtooI,3158
|
80
81
|
sglang/srt/debug_utils/text_comparator.py,sha256=pg58q3fzsnd3rJKRgZTdcOviOtAv8pSYZdwf-TLffMM,5522
|
81
|
-
sglang/srt/disaggregation/decode.py,sha256=
|
82
|
+
sglang/srt/disaggregation/decode.py,sha256=xPXKHz0e8O9GZetHiGVQoN8iIwEA1GwO8jj0NkCzgp4,33884
|
82
83
|
sglang/srt/disaggregation/decode_schedule_batch_mixin.py,sha256=sUXmqiJGwuYoJvZjRCgTMVEN7bLefnEUlCTJpVA6ecI,6416
|
83
84
|
sglang/srt/disaggregation/kv_events.py,sha256=yFbtwOeblcCmOXTjg00TopxnyjkmCBQIVz46KB8jetY,13555
|
84
|
-
sglang/srt/disaggregation/launch_lb.py,sha256=
|
85
|
+
sglang/srt/disaggregation/launch_lb.py,sha256=Elw-J-97jTA70Ml1EMp_J-k9X9H5WHTWOC2XEvmyJRY,3827
|
85
86
|
sglang/srt/disaggregation/mini_lb.py,sha256=bpnz6d90nv7vAoiPxmxFKlM1Gjct0R4IPkF9SwwBk9I,14504
|
86
|
-
sglang/srt/disaggregation/prefill.py,sha256=
|
87
|
+
sglang/srt/disaggregation/prefill.py,sha256=6SN5df3PGWOixdEaTVR-INJjeSNXGP4X0y2IepsCZFs,24090
|
87
88
|
sglang/srt/disaggregation/utils.py,sha256=ql5p9yjBCRcR0YMgcgRK6tH0kPGvLNTUgeXBr_BUcoI,12198
|
88
89
|
sglang/srt/disaggregation/ascend/__init__.py,sha256=-lxnica6fZYmYNpKwmE8yESUpQ5Sxf2DiZoBHzboKc8,146
|
89
90
|
sglang/srt/disaggregation/ascend/conn.py,sha256=FOYrGtEhj58iTjhYT1eP96DpyxBLFFR87icqYCzWmCY,1215
|
@@ -96,13 +97,13 @@ sglang/srt/disaggregation/common/utils.py,sha256=SxRhAWisNK8seGhb5BXBJ5u53DF7yeK
|
|
96
97
|
sglang/srt/disaggregation/fake/__init__.py,sha256=jJGWdXwaQiGIoR6atKqkQfkJmVyQ09l55VUN2WjwaeY,77
|
97
98
|
sglang/srt/disaggregation/fake/conn.py,sha256=oD1DArn1yDFZCu-X6p93uSLlAXEkt9lYxERICMznxGw,2286
|
98
99
|
sglang/srt/disaggregation/mooncake/__init__.py,sha256=0TgqkAdQI1YynbHY6c0QISvVoOSk-0SwCIq5rjPSmgE,156
|
99
|
-
sglang/srt/disaggregation/mooncake/conn.py,sha256=
|
100
|
+
sglang/srt/disaggregation/mooncake/conn.py,sha256=BrOcdnqk7Ut90qDqajNzQx3qTBlnsVhLmMgUgXVGCdg,62677
|
100
101
|
sglang/srt/disaggregation/mooncake/transfer_engine.py,sha256=-ulLhz6DBDsmEjwNjjH5Pj8ngZKISgwBc_zL3ViGDN0,4761
|
101
102
|
sglang/srt/disaggregation/nixl/__init__.py,sha256=qODVPIGWUXKXq4zsRIcMYoAoAeg6nBIN9vdQOlVMANE,136
|
102
103
|
sglang/srt/disaggregation/nixl/conn.py,sha256=eSof87fG21Dd4COszfnbeXIxne3TWvw0mSvCOkjsBZc,20323
|
103
104
|
sglang/srt/distributed/__init__.py,sha256=jFOcyt-wFAPMBUAf9zkZalNQlt-4rqmT6pCKBz1E4qo,149
|
104
105
|
sglang/srt/distributed/communication_op.py,sha256=IBnFUdMftK_VSTMMMitGveonorFUUVNL4guqO31cMSc,1130
|
105
|
-
sglang/srt/distributed/parallel_state.py,sha256=
|
106
|
+
sglang/srt/distributed/parallel_state.py,sha256=KteVN6j7i_c7fkoTInY2MiMf5-0T2Pvb8SYA-3U80n8,61308
|
106
107
|
sglang/srt/distributed/utils.py,sha256=aaCxATncLGnVgB0WlGpBdee0behKW8Dy_dakqcuKSaQ,8497
|
107
108
|
sglang/srt/distributed/device_communicators/cuda_wrapper.py,sha256=3jvPG-Ow5UBLiXhfx8T8snR7crSZbPpARAggsDPWq7k,7038
|
108
109
|
sglang/srt/distributed/device_communicators/custom_all_reduce.py,sha256=p-GLYYnMSjcUvK30qcwYhXEJwGrOz6rR99p_23SWFj8,16570
|
@@ -116,13 +117,13 @@ sglang/srt/distributed/device_communicators/quick_all_reduce.py,sha256=4j1_E4azo
|
|
116
117
|
sglang/srt/distributed/device_communicators/shm_broadcast.py,sha256=IrSrnpZnii0EJTS1CYRwEwE7gyHxJBVgI2QuJS3AKW0,20906
|
117
118
|
sglang/srt/distributed/device_communicators/xpu_communicator.py,sha256=ajW6132BvA6jkeipEIgN27TFycI0U06Ih2Z8WNjlA4s,1593
|
118
119
|
sglang/srt/entrypoints/EngineBase.py,sha256=yKN76witT2jz1zhmLHmPNLGMpK2UiOTaKQ2KPD8l99U,2594
|
119
|
-
sglang/srt/entrypoints/engine.py,sha256=
|
120
|
-
sglang/srt/entrypoints/http_server.py,sha256=
|
120
|
+
sglang/srt/entrypoints/engine.py,sha256=VamDmlSFQzx7vdnKpVKbAqwdMJx0HHixDcUB8y2wAS8,31748
|
121
|
+
sglang/srt/entrypoints/http_server.py,sha256=epmh6xb3IKQTF9o0QpZeCUnPuZqJhhfKLlVXxB3uZJY,38177
|
121
122
|
sglang/srt/entrypoints/http_server_engine.py,sha256=_--j4U04OeJLlnnv1f0XmCd_Ry0z1FlhkrbePX8rYV0,4938
|
122
123
|
sglang/srt/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
123
124
|
sglang/srt/entrypoints/openai/protocol.py,sha256=2XfURpoICsk4UZs4W9lm2A1yXNC-iwqSdZOuof0FXjo,19183
|
124
125
|
sglang/srt/entrypoints/openai/serving_base.py,sha256=epD6J7K72p6TP8o2dGYf-a76nXeF80vFhPRpWts6684,5445
|
125
|
-
sglang/srt/entrypoints/openai/serving_chat.py,sha256=
|
126
|
+
sglang/srt/entrypoints/openai/serving_chat.py,sha256=wscn5l3Kcgk0fqhxke31_ALc8h3mptwdIzYX5dpTWEI,38853
|
126
127
|
sglang/srt/entrypoints/openai/serving_completions.py,sha256=emIutVmnJgOgGRuAqdB80-kVHUfQbE67n1VS-76o4QY,16690
|
127
128
|
sglang/srt/entrypoints/openai/serving_embedding.py,sha256=hqPt2ELpT1yQ8sBXo801aLJ3sExoPXs_K5ZQtC2vpAs,6274
|
128
129
|
sglang/srt/entrypoints/openai/serving_rerank.py,sha256=8n6y5kC6UhRpWrDtzH0eIp0dznW12FT60MLCR4bvD2U,3333
|
@@ -131,10 +132,10 @@ sglang/srt/entrypoints/openai/usage_processor.py,sha256=9LTB5rqdRuMKyZrIXiUBuF_W
|
|
131
132
|
sglang/srt/entrypoints/openai/utils.py,sha256=DT9quW0F1DX1P9NAuMxpERgXcNYKKtm7rd7J1m7EaDQ,2112
|
132
133
|
sglang/srt/eplb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
133
134
|
sglang/srt/eplb/eplb_manager.py,sha256=Wt7w4L5g1BSsXx1mqoGo8WjkB55f4nGB4KqC3y_ijl8,3394
|
134
|
-
sglang/srt/eplb/expert_distribution.py,sha256=
|
135
|
-
sglang/srt/eplb/expert_location.py,sha256=
|
136
|
-
sglang/srt/eplb/expert_location_dispatch.py,sha256=
|
137
|
-
sglang/srt/eplb/expert_location_updater.py,sha256=
|
135
|
+
sglang/srt/eplb/expert_distribution.py,sha256=4EdteobZ8eictPXBy0X_BKqY56GrX4j6vtPV3rnyegg,31690
|
136
|
+
sglang/srt/eplb/expert_location.py,sha256=A9zkr4lCl8480WlPVIMosdjSrMI1y_ym_v1iRIjJP68,16753
|
137
|
+
sglang/srt/eplb/expert_location_dispatch.py,sha256=vA0o-7bXf847BQAVCqElWKEpofZLAIsir_d0pew2KNQ,4178
|
138
|
+
sglang/srt/eplb/expert_location_updater.py,sha256=eMtJVMCRklfvKPbFiDKy85f5J9s_krJbpRCSArYZjVs,21157
|
138
139
|
sglang/srt/eplb/eplb_algorithms/__init__.py,sha256=c6fo4qM8N0p5DyyfGp9fxqc2wkxvzSJBzJFRG1I1leg,1959
|
139
140
|
sglang/srt/eplb/eplb_algorithms/deepseek.py,sha256=mMZT7zAAArccdRS0xXxifvMb3qn9enSt426uUTKeiq4,8340
|
140
141
|
sglang/srt/eplb/eplb_algorithms/deepseek_vec.py,sha256=Vzy5Iarua1VgVHzjBNZaVV_vt1LY1BLtJz7PmzB701k,10654
|
@@ -144,7 +145,7 @@ sglang/srt/function_call/base_format_detector.py,sha256=FKBzsGFHfNl3Wvccsdvv9ftj
|
|
144
145
|
sglang/srt/function_call/core_types.py,sha256=wLUsW8mUA-i-ISz5QUDL7Ejq72W-K1HIhFa9Wm-_oA8,786
|
145
146
|
sglang/srt/function_call/deepseekv3_detector.py,sha256=WzJbwCe8DoOi8guX9pdVMd70CViVrwoaxi8PZwIC9pg,9712
|
146
147
|
sglang/srt/function_call/ebnf_composer.py,sha256=HvLTgfNnBNKFKW-L36DKh07yRLbdTYjSfbTcLRUxZUc,14948
|
147
|
-
sglang/srt/function_call/function_call_parser.py,sha256=
|
148
|
+
sglang/srt/function_call/function_call_parser.py,sha256=t4ISHoB_xF7HFy7DF8zCJ0U8EwWivbc_DNlLX1o8Xb0,8107
|
148
149
|
sglang/srt/function_call/glm4_moe_detector.py,sha256=TD67qS7T-9iR4-P5fhrUbqqYWEYVTb30dDNd7lGj4Rk,6934
|
149
150
|
sglang/srt/function_call/kimik2_detector.py,sha256=7unW_GwH7I6jrh2BZbw22mWRZzQ0OMTYDz_xVX5abPU,10116
|
150
151
|
sglang/srt/function_call/llama32_detector.py,sha256=trZja7IXc2IWUko5PRj7p4pRU6XCVjtxr-7qJNr0EWo,3647
|
@@ -152,6 +153,7 @@ sglang/srt/function_call/mistral_detector.py,sha256=Ts2HrJdu5r2lCCMVKPZfnCds9pt1
|
|
152
153
|
sglang/srt/function_call/pythonic_detector.py,sha256=yAatItKtVDf9uhlB78wPWKP3fbefLJDNGGzFV5ey-YA,8756
|
153
154
|
sglang/srt/function_call/qwen25_detector.py,sha256=nv83_sipZMU6Vie3J4HeNiZVCSRU5ei7601j50779HA,5181
|
154
155
|
sglang/srt/function_call/qwen3_coder_detector.py,sha256=3QAoK9W3YFPrx_j3xIsDpmQSnbX0BixMAlJ6BoNJo8o,5517
|
156
|
+
sglang/srt/function_call/step3_detector.py,sha256=SAibrispu0peDQzqOG2-V93KGHtV6Ud7a38vlnhTunA,17442
|
155
157
|
sglang/srt/function_call/utils.py,sha256=__ImDF2kNyoLWsYO5RYoryvy1mmgEjnjXlCvLv-uLCM,1695
|
156
158
|
sglang/srt/layers/activation.py,sha256=uhfhh10N5iLoLEBCvFPRjCfDxu5jXe1ehHJb3ISIjig,7840
|
157
159
|
sglang/srt/layers/amx_utils.py,sha256=1mENgHK2B8mgaD1oMtgbZ15Jmy_Uu1QueBmo09Ff2iA,2865
|
@@ -186,7 +188,8 @@ sglang/srt/layers/attention/merge_state.py,sha256=OnWmNV6LYTUj0y8SCy_IK7A9q6v9bZ
|
|
186
188
|
sglang/srt/layers/attention/tbo_backend.py,sha256=CBnSDUmDvT-Tbhi9NHNo1LLkgUAcIsWMJgKa-sAIKW8,9318
|
187
189
|
sglang/srt/layers/attention/torch_native_backend.py,sha256=RsI4lYiQJAj-Xy0vKkzbyKOWHAVPOD9b0n0dEehwlos,9496
|
188
190
|
sglang/srt/layers/attention/triton_backend.py,sha256=AryrPc4kzioxkiucPkApMA__0HoQTKOHNpwN0GEgm98,36923
|
189
|
-
sglang/srt/layers/attention/
|
191
|
+
sglang/srt/layers/attention/trtllm_mla_backend.py,sha256=axNZ4VKRqbLvLFhmFjT-CESXjtGtu5sa6VypQdOXbhQ,13356
|
192
|
+
sglang/srt/layers/attention/utils.py,sha256=lx_jNw2VwlBe2VnDb1eXRRdN9WArw9rdWHTHqndUEFk,3174
|
190
193
|
sglang/srt/layers/attention/vision.py,sha256=zI1Pq2Tx4SwOzYhIarxNtlTiZeVMWxVf8j-Pf7xhzCA,18111
|
191
194
|
sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=eN0Lqpu5h27lMPuRnisX4jrU0WR061pCFSrh3vLlSD0,18936
|
192
195
|
sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=FbgrPO5GvEGEvojV7Ss0jX7384e9vuzX2goDCQuP1Zk,31124
|
@@ -194,7 +197,7 @@ sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=ImpCuxszoeVdr6
|
|
194
197
|
sglang/srt/layers/attention/triton_ops/merge_state.py,sha256=v9nD01a5eTnkwZxMwERtrrRfC5rs6GxkYOpErkAPcYI,2877
|
195
198
|
sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=waZsmpKIp8rTgFSoM4QMabJuLaB3yW6ltOzAKJksBoE,6260
|
196
199
|
sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py,sha256=664WnAJ91EiCUZOcnVDfbTQf4uGJ4ZDZB1CbxpEUFZc,13866
|
197
|
-
sglang/srt/layers/moe/cutlass_moe.py,sha256
|
200
|
+
sglang/srt/layers/moe/cutlass_moe.py,sha256=jprUaoU1PbfwiEP_yTE5Z8ulviQoZWI8tRk0lsNABzE,14348
|
198
201
|
sglang/srt/layers/moe/cutlass_moe_params.py,sha256=9NRCmgP_Ug3gGqCcpi-x-QRbLjCNpw8792gKXwZsbEU,6522
|
199
202
|
sglang/srt/layers/moe/cutlass_w4a8_moe.py,sha256=bc8s5Oc36pCF0VozxZuqFOOU2fov-4wGPlyduye3Imk,7296
|
200
203
|
sglang/srt/layers/moe/fused_moe_native.py,sha256=SkOFgU23aZfHmLhnkVhdUWGx0-2wbo6uu9ohKBp2yOI,3486
|
@@ -202,11 +205,11 @@ sglang/srt/layers/moe/router.py,sha256=UrPieRvemN7Ew48gtG7DA2xhNDBRSnZxzugTEBI-0
|
|
202
205
|
sglang/srt/layers/moe/topk.py,sha256=ttPFvXzTY0eyh6UH8fJZCjyDp-R9EssSP8m229MxQ_4,26925
|
203
206
|
sglang/srt/layers/moe/ep_moe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
204
207
|
sglang/srt/layers/moe/ep_moe/kernels.py,sha256=UFH-XacP3aBjAcn6_SeC641jGzjSrY0fz50IB9URix4,42706
|
205
|
-
sglang/srt/layers/moe/ep_moe/layer.py,sha256=
|
208
|
+
sglang/srt/layers/moe/ep_moe/layer.py,sha256=zMhZy01cPePBSy4y_OLKT6XYxEZjtJ2Ec6CD69d2TXc,26911
|
206
209
|
sglang/srt/layers/moe/ep_moe/token_dispatcher.py,sha256=CJhFTtOydsLSXMYNfzAASPI5p_oP7c4krGwX4bBcT1s,22909
|
207
210
|
sglang/srt/layers/moe/fused_moe_triton/__init__.py,sha256=4NXZHbCw-G-uSnNUj4up0yh3xBDPnT-x0pdoIr0lku8,831
|
208
|
-
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=
|
209
|
-
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=
|
211
|
+
sglang/srt/layers/moe/fused_moe_triton/fused_moe.py,sha256=Yb7LvdCQWonJC05_4UOMt3jQYWmRl-AkdY7H5EVwKhM,57575
|
212
|
+
sglang/srt/layers/moe/fused_moe_triton/layer.py,sha256=7DIbnX1QyVetaKh6ZTixTEedsL0QDmMd8_3pmFU9xnU,27716
|
210
213
|
sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py,sha256=HOEJJyehKTUIjkcsTc29aEXHqVLgDlv_jQL5fjvuUxU,5856
|
211
214
|
"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
|
212
215
|
"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
|
@@ -387,7 +390,7 @@ sglang/srt/layers/quantization/awq.py,sha256=gLEOx6QoGQ0McBEURXPVidKGsdNUjqc9sJw
|
|
387
390
|
sglang/srt/layers/quantization/awq_triton.py,sha256=4XwJbRNlFmlvjbMGtWF1Wvk26Kf96162vNEmuI5Kars,11737
|
388
391
|
sglang/srt/layers/quantization/base_config.py,sha256=CiSxG5iuOa-12V9kIOh0Fu8Y7knZxfFbbNGTo6nEaRE,7173
|
389
392
|
sglang/srt/layers/quantization/blockwise_int8.py,sha256=3avetVUBjCiuYWBJQbElbVXWpx0SgsFsDc5F9F_zHgA,13879
|
390
|
-
sglang/srt/layers/quantization/fp8.py,sha256=
|
393
|
+
sglang/srt/layers/quantization/fp8.py,sha256=DAateV96FCn2dWpgT_Zju2f0ARuAMOMd3HuNquXGk_E,48644
|
391
394
|
sglang/srt/layers/quantization/fp8_kernel.py,sha256=8alryD9sEROh9Dh4cdPrGIpuOPbT6Hx6PNSe8fJc9zM,40856
|
392
395
|
sglang/srt/layers/quantization/fp8_utils.py,sha256=6FVR6_Y8akP4ihCaGG_bLYurcC_PShPtiPgiEvGN5bE,25605
|
393
396
|
sglang/srt/layers/quantization/gptq.py,sha256=3q9xfq5sJJHcrVr9C8-l9JdcLFvwKAAfWJEfZW6CzLs,39145
|
@@ -401,11 +404,11 @@ sglang/srt/layers/quantization/petit.py,sha256=74Jn0eICq23v_b4rEctDaYTINtbqkdM6I
|
|
401
404
|
sglang/srt/layers/quantization/petit_utils.py,sha256=-gy4zMhqNoIA1R0n7-5C0efV54jHonCUgPDUUFjGsyM,3245
|
402
405
|
sglang/srt/layers/quantization/qoq.py,sha256=jM96uJfKz3vo1B6SSIrQXNT3vnD3UJrepK2eY-tSQU4,8139
|
403
406
|
sglang/srt/layers/quantization/scalar_type.py,sha256=nBk4THjeRWMGW3hKWRdrjfQ0gwpuBxmYqapDBaRpnr4,12395
|
404
|
-
sglang/srt/layers/quantization/unquant.py,sha256=
|
407
|
+
sglang/srt/layers/quantization/unquant.py,sha256=vgI2G1iHpMr2ys1-HaQ_YIXJN0z1m9uM6MpJh_1Ktrg,12108
|
405
408
|
sglang/srt/layers/quantization/utils.py,sha256=9ZmfS0MMqueQ6zIxMIFoQy2OFBQ5vHjOHBgVvUn7ews,16213
|
406
|
-
sglang/srt/layers/quantization/w4afp8.py,sha256=
|
409
|
+
sglang/srt/layers/quantization/w4afp8.py,sha256=wa5t0g2IwVFcwHxZ213f5Vsnt8P4fum7WVoxvf0llpw,11092
|
407
410
|
sglang/srt/layers/quantization/w8a8_fp8.py,sha256=I_W9A4Pnluaf-SaT8zq-tAJTt1acpxfE_kG5mqdc5cE,10250
|
408
|
-
sglang/srt/layers/quantization/w8a8_int8.py,sha256=
|
411
|
+
sglang/srt/layers/quantization/w8a8_int8.py,sha256=VXGAMKMlRU7k6c-WRXDExBTOa2oLODRFq-RIZXGsI-c,35013
|
409
412
|
sglang/srt/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
410
413
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=DsPCI82A4rqI6mjKo-WorIKUweppFV7-16Qku-zW9_g,25897
|
411
414
|
sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=vwcgwGuPhH2kHBfg7DnsndzffrbZx8xuFsl9Qeegd9s,24286
|
@@ -585,44 +588,56 @@ sglang/srt/lora/triton_ops/gate_up_lora_b.py,sha256=QURCYxHNR8Ls4SQtt3dvdgjvdDVh
|
|
585
588
|
sglang/srt/lora/triton_ops/qkv_lora_b.py,sha256=iz5scFNo2YFTeiM8beWg9Z1oZI-6AM_T1wBMCQ6qp2Q,6485
|
586
589
|
sglang/srt/lora/triton_ops/sgemm_lora_a.py,sha256=Ksova04wgeGsFqGOXWqJtMYaHgyUYcx8VU42BZQOkVA,5129
|
587
590
|
sglang/srt/lora/triton_ops/sgemm_lora_b.py,sha256=VqCAFvUtq_l-0RGIkx3W_fzD55QcW2FAcqpvSHOBFp4,5115
|
588
|
-
sglang/srt/managers/cache_controller.py,sha256=
|
591
|
+
sglang/srt/managers/cache_controller.py,sha256=qQrYJk8DG7DDwdmAe-vOKUW36E_OEFP4rBCrKPXldOE,29265
|
589
592
|
sglang/srt/managers/configure_logging.py,sha256=8sNXZ2z9pBWOwn-X3wyz013Ob8Nbm1zDxRkxoZjH-l4,1633
|
590
|
-
sglang/srt/managers/data_parallel_controller.py,sha256=
|
593
|
+
sglang/srt/managers/data_parallel_controller.py,sha256=omM1s7os0rbMQSDlrCJcdLTWHx0eGxJ-DBVf9PX4kow,12412
|
591
594
|
sglang/srt/managers/detokenizer_manager.py,sha256=SpLxTsSPKBZfD-ZMhJ5zpPPGuUb8PmcYgFSL9CsurU4,10696
|
592
|
-
sglang/srt/managers/io_struct.py,sha256=
|
595
|
+
sglang/srt/managers/io_struct.py,sha256=EdQPJIZL3u_9eYSPi3sO8vBlRKBZWPwgWWWd-y1bvvI,38017
|
593
596
|
sglang/srt/managers/mm_utils.py,sha256=VrJiv0k_zDa83BsfVv8rmckgXKsvF0Wz88bCAb6R1as,29601
|
594
597
|
sglang/srt/managers/multimodal_processor.py,sha256=mLnGcUHIvjruwoVhqiz4j7RMYMsZnvQMH8JnKCITDlY,1805
|
595
598
|
sglang/srt/managers/schedule_batch.py,sha256=xmWSPAsllmPaWtKNrf-P8IX6fuQMTD-vZuk1y01vUjA,76289
|
596
599
|
sglang/srt/managers/schedule_policy.py,sha256=BFYItMXtrsO5157tpFhYwLpZ8NSlzR4_gNZC1iE10D4,22400
|
597
|
-
sglang/srt/managers/scheduler.py,sha256=
|
600
|
+
sglang/srt/managers/scheduler.py,sha256=JErd7exLcqADWzVV1lr2WSWKOpZfGUXuDhEBS9aWViw,100218
|
598
601
|
sglang/srt/managers/scheduler_input_blocker.py,sha256=zP8xU_UmU2H0AB6sEqvivDcDB1QDgTauNDYDIJ7Nez4,3683
|
602
|
+
sglang/srt/managers/scheduler_metrics_mixin.py,sha256=-1IOE30eOoTvvpz-Xg9J4UcamwAJle2-odFJ9vrinLE,9341
|
599
603
|
sglang/srt/managers/scheduler_output_processor_mixin.py,sha256=Ei-9lyfrSQAlL9_ULuJLAhA7qpvUzjsBDzBBTDdnt4Q,31394
|
604
|
+
sglang/srt/managers/scheduler_profiler_mixin.py,sha256=GnR1SALuj_JbsENfmpiVgVcJWtGQn8hJ8TERkLB7h1c,10701
|
605
|
+
sglang/srt/managers/scheduler_update_weights_mixin.py,sha256=cQYdfHSgqLR7FeWMZl1V_lXMSKw99WGUa9gdiYUMXLU,5334
|
600
606
|
sglang/srt/managers/session_controller.py,sha256=dzlMNZlo20FTSl64QqK7y7pElsdCy8ICOWWBPTBVwgs,6040
|
601
|
-
sglang/srt/managers/template_manager.py,sha256=
|
602
|
-
sglang/srt/managers/tokenizer_manager.py,sha256=
|
603
|
-
sglang/srt/managers/tp_worker.py,sha256=
|
604
|
-
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=
|
607
|
+
sglang/srt/managers/template_manager.py,sha256=VknbMRG1HSGUezGIGBmb_LIx1A0heyKXnSs7veHHG14,10252
|
608
|
+
sglang/srt/managers/tokenizer_manager.py,sha256=zdJgKu1P2RB89snecRkf_B--FTkidqGnGClA04ZnNvc,79676
|
609
|
+
sglang/srt/managers/tp_worker.py,sha256=Y8GEgEI9Y4ayw4K71yRHDzeVX43JjTBkf3vFf8RfS9w,11764
|
610
|
+
sglang/srt/managers/tp_worker_overlap_thread.py,sha256=3KQQ2YkyswgtouByhfPPq5mCISsMstn9CEa1i4qv-Xg,10998
|
605
611
|
sglang/srt/managers/utils.py,sha256=9_VGE48EK0PXVJ26aYvbRJ6n7gIZALvCcf6uZCccCgM,1369
|
606
612
|
sglang/srt/mem_cache/allocator.py,sha256=id4riucsG9d-P1ikj3-DLJbzhM8-MuJfvDmB8H4g9-o,23364
|
607
613
|
sglang/srt/mem_cache/base_prefix_cache.py,sha256=hLS2ncTMAz7Kpdk5pNwn5c6g8b61_K9OCBL4Vj1xsYc,2801
|
608
614
|
sglang/srt/mem_cache/chunk_cache.py,sha256=FU_fq8e_dodgU8EkRqE4Jr0sKwCXQnKmapO88k6_JfU,3207
|
609
615
|
sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
|
610
|
-
sglang/srt/mem_cache/hicache_storage.py,sha256=
|
611
|
-
sglang/srt/mem_cache/hiradix_cache.py,sha256=
|
612
|
-
sglang/srt/mem_cache/memory_pool.py,sha256=
|
613
|
-
sglang/srt/mem_cache/memory_pool_host.py,sha256=
|
616
|
+
sglang/srt/mem_cache/hicache_storage.py,sha256=t7A8eIRdSep_005M3_BKGMSUWgKWBQL8RoBRrpJu_fQ,6713
|
617
|
+
sglang/srt/mem_cache/hiradix_cache.py,sha256=QbKT2NKLuVe-1AqEc_njtZHXrq8d6WiNNbLa6Qio9qI,25818
|
618
|
+
sglang/srt/mem_cache/memory_pool.py,sha256=i-QhFrYuaAFcMOG7QH6SJyJ8hFzVRS5fjxwKmae8f94,37064
|
619
|
+
sglang/srt/mem_cache/memory_pool_host.py,sha256=M5dTu4BiEEiTlD7vtctd_LQrCODS1iradGaFtHaRkXM,25385
|
614
620
|
sglang/srt/mem_cache/multimodal_cache.py,sha256=wZl2KeEl3xeoEsYdH33UoM-FO8kqfLo_XUgereJVvoM,1348
|
615
621
|
sglang/srt/mem_cache/radix_cache.py,sha256=kp4JiVxh3eS4MsFxGKIYjYAb14B777qc1bHrABPqBMc,19101
|
616
622
|
sglang/srt/mem_cache/swa_radix_cache.py,sha256=4qt_gS7GuHiekd6VvKkx54dB2GHJzNA_kj71Np6jTDA,40300
|
623
|
+
sglang/srt/mem_cache/mooncake_store/mooncake_store.py,sha256=vFDsTE1a-6FP_AidlGKrlX9-oZvdxh8rnQiFDd-UcE8,9748
|
624
|
+
sglang/srt/mem_cache/mooncake_store/unit_test.py,sha256=jMdJgU41VscKS-mn_AVZE8LQbb_3MWQ57i9V3OCWLI4,1007
|
625
|
+
sglang/srt/mem_cache/nixl/hicache_nixl.py,sha256=GU2J2335razBIIEqV2L44CR8N-QYKmhbHEDGa61EFEE,6170
|
626
|
+
sglang/srt/mem_cache/nixl/nixl_utils.py,sha256=i2C70Ct2xdZtR_6OSL7uQk7ped1TieSpdUKo8yXdc08,8672
|
627
|
+
sglang/srt/mem_cache/nixl/test_hicache_nixl_storage.py,sha256=TBtN12muLFXZ296mK2d3TSTyj8qhMo5kAYWLpSjLBhY,8017
|
628
|
+
sglang/srt/mem_cache/storage/hf3fs/client_hf3fs.py,sha256=k9ZtqKfWdJh19jLyRu0iXJEciXXuqFcEuMXej3hJhmg,5178
|
629
|
+
sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py,sha256=H0X4v5AWs4uTHoBGgb9BgfKf3WZ3reZKpLNxmL1dTbI,9230
|
630
|
+
sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py,sha256=g2h0Woa2CK39pRTigHCVR_hq095dTaC70lCIAIs9THM,1089
|
617
631
|
sglang/srt/metrics/collector.py,sha256=FH6Wil2lMK7d7q74CfxfdULCaHKDXeAoo8UBZqqdepM,20289
|
618
632
|
sglang/srt/metrics/func_timer.py,sha256=VFyNRrbnKVCwnQsrlLin1lITJfjQpf9m8sGPqL5LIsQ,3438
|
619
|
-
sglang/srt/model_executor/cuda_graph_runner.py,sha256=
|
633
|
+
sglang/srt/model_executor/cuda_graph_runner.py,sha256=ViEnpEtqUeUOtd42WipMTrXWFaQ8jrkupEZ0UYrBKmE,32628
|
620
634
|
sglang/srt/model_executor/forward_batch_info.py,sha256=NvUhReevoy6UfO4991P_5MPQyfefC3BOoTwTqUwMbYk,38430
|
621
|
-
sglang/srt/model_executor/model_runner.py,sha256=
|
635
|
+
sglang/srt/model_executor/model_runner.py,sha256=CtFvyzmUMX_-QMtytmBEWc6a7Q4SZsktOPjZO3ANGp4,73144
|
622
636
|
sglang/srt/model_loader/__init__.py,sha256=zGZkOBz1zx-pkaIy47BasL3fjDlAcxAXUTjInOhXHAE,919
|
623
637
|
sglang/srt/model_loader/loader.py,sha256=wxSUYrqv23w9yHYy9Lm0ozWggs9pf6Co4yqe1UO8PZk,59799
|
624
638
|
sglang/srt/model_loader/utils.py,sha256=svSrPQxViBz_-0_sByu4coCYrzJ51-4FCi_bFqa6rDo,4474
|
625
|
-
sglang/srt/model_loader/weight_utils.py,sha256=
|
639
|
+
sglang/srt/model_loader/weight_utils.py,sha256=2UxbNYzoZxIIrDhsEOk6M-ofFg5s1UMtV1j23XRbnq4,38129
|
640
|
+
sglang/srt/models/arcee.py,sha256=Q6fujRESEnljzs8ls3XGsPtWxzfKfUa0QAvAekYzeBY,18981
|
626
641
|
sglang/srt/models/baichuan.py,sha256=HbvlErnkCSK4pRQYCSDxMcrn-1DQyfiNoeDcnRrJas8,15807
|
627
642
|
sglang/srt/models/bert.py,sha256=ODJe8YfNRP-hHsomFWk4_QpcuiSsNfjzGf256EDS0Pc,15802
|
628
643
|
sglang/srt/models/chatglm.py,sha256=cajLN9caBl09e0TwOFkiTTKDqwlbmHo_yS-NCjdeQW8,13957
|
@@ -632,7 +647,7 @@ sglang/srt/models/dbrx.py,sha256=4pn_fdoATg01VEqNnIAxNEsKV5XU7gwHyd289eydq1s,155
|
|
632
647
|
sglang/srt/models/deepseek.py,sha256=sqobTr9a9c5pNLNJZE-WrJIE_qBq0lC5gCGv9NpGU_Q,17364
|
633
648
|
sglang/srt/models/deepseek_janus_pro.py,sha256=td8xGs6ARfJ8AQCYwUhMOZoWigrAs7m3trF5-kXCqik,70418
|
634
649
|
sglang/srt/models/deepseek_nextn.py,sha256=47fehxRdiOizr0rdLg5f1fzQEx6gGAOcDcWKtblloyk,5928
|
635
|
-
sglang/srt/models/deepseek_v2.py,sha256=
|
650
|
+
sglang/srt/models/deepseek_v2.py,sha256=eHVdyXEiW7z0nIQByKt_h_Slfi6N-n9DWtKsBuBT9xE,103640
|
636
651
|
sglang/srt/models/deepseek_vl2.py,sha256=7X3gI4DE7guUtNJvMLf06jO8MUHKa2Aan8evZg5hsXc,13061
|
637
652
|
sglang/srt/models/exaone.py,sha256=TpO-rtCpEZ8Ua7hGFnS8l2oAYhY0Pij50grc9WQ2mvc,13576
|
638
653
|
sglang/srt/models/gemma.py,sha256=2atKwFN5wCsJCmBRmURX9vaCcFjxlFirL7xsnG5KPlI,14180
|
@@ -644,14 +659,14 @@ sglang/srt/models/gemma3n_audio.py,sha256=isgKfjA5UieYawxU6medL2ssXlzYPqAbagDBnL
|
|
644
659
|
sglang/srt/models/gemma3n_causal.py,sha256=kBDlpSWAg6ZDmUPe08Q7sj5CbdVD_0h07zwJw8sKu7I,36335
|
645
660
|
sglang/srt/models/gemma3n_mm.py,sha256=pL_fvnkz9fKaC2Afms5KG3Me3u5sp1C2-mAUhqPGrQ4,18701
|
646
661
|
sglang/srt/models/glm4.py,sha256=2VQzUqFkQTy_2nfkxP9SF6_9kKLTZUExGRjge7r99Es,11265
|
647
|
-
sglang/srt/models/glm4_moe.py,sha256=
|
662
|
+
sglang/srt/models/glm4_moe.py,sha256=fV4gfrnhXPUTa4NnbzZha_euKpjbLi3JG7QGmJsiW4E,40007
|
648
663
|
sglang/srt/models/glm4_moe_nextn.py,sha256=cWB6o3w7xBvgi2ouGKsqZ3iovKH65QiRQul42wcgzMk,5897
|
649
664
|
sglang/srt/models/gpt2.py,sha256=kclhxEs8oJk1KCyhmAqo7rZqecVGGHYkc-a1WZi3aIk,9841
|
650
665
|
sglang/srt/models/gpt_bigcode.py,sha256=1D6bi8Zu760gCRZkvdLHFcg8kCkY35ARwQYaMDtYhl4,10307
|
651
666
|
sglang/srt/models/granite.py,sha256=5WOJyNYAlt5RNHSexNfPNihhSxIMd7wPzju1cTixKig,20852
|
652
|
-
sglang/srt/models/granitemoe.py,sha256=
|
653
|
-
sglang/srt/models/grok.py,sha256=
|
654
|
-
sglang/srt/models/hunyuan.py,sha256=
|
667
|
+
sglang/srt/models/granitemoe.py,sha256=Yr1pEOS_8QopQKBIiDpFpMXZ0Wkc1REyPorM3eDTjNE,13808
|
668
|
+
sglang/srt/models/grok.py,sha256=TX2rh_dOy7j20v5hdjkf9Na63SZhFhw4ZFuNY_Re3Aw,28284
|
669
|
+
sglang/srt/models/hunyuan.py,sha256=RSZErx-Swt65kmfvSXJQJJ6KhjucuNY4UUVLWC8hWaA,31102
|
655
670
|
sglang/srt/models/idefics2.py,sha256=U3khd3hbdawJeRNXsxmaKHdssOCT5TPOZ1D-2_zHoQo,12079
|
656
671
|
sglang/srt/models/internlm2.py,sha256=F_iNY1gUqzAjAuUatcE47gnrcoTh5_08PY2Rw9tKr9M,13150
|
657
672
|
sglang/srt/models/internlm2_reward.py,sha256=ndfGmyqYZbVZ7C7rJ-v9oK3wa-EpoBGybS8MlyKZi2E,2522
|
@@ -660,7 +675,7 @@ sglang/srt/models/internvl.py,sha256=o6XSAvnMYK5tTPbln9RI9BfRfAQZBE8_xmGPffrznnQ
|
|
660
675
|
sglang/srt/models/kimi_vl.py,sha256=XulRiufQzOSWZe8-bUl2OEdznvsVU9OBsEYipaX3YkM,12877
|
661
676
|
sglang/srt/models/kimi_vl_moonvit.py,sha256=M5L7AJOJ2Zh2pqLZAq8aRqhbTSlipr8XOoD3ix6o2sU,23908
|
662
677
|
sglang/srt/models/llama.py,sha256=Nsxv2s1sOmLnZsTHkwbTh53cUFEQ2fnKDQi5BFbFcsk,28994
|
663
|
-
sglang/srt/models/llama4.py,sha256=
|
678
|
+
sglang/srt/models/llama4.py,sha256=6FLn2l7E8zRNWCvHPQ8KOOlyB_3lL9m5WK3mBMgz9zY,18886
|
664
679
|
sglang/srt/models/llama_classification.py,sha256=4QWTFaUZIFKYZvEzs8bx8VkOZNIwdYCLrnwrdAw4QK0,3108
|
665
680
|
sglang/srt/models/llama_eagle.py,sha256=Ubh_jmtfiOnriwvHgQT0ZGID7JvYvdSi_QGHOIkEgPE,5028
|
666
681
|
sglang/srt/models/llama_eagle3.py,sha256=715soylDE3kOMWskbPy_70BFxaSc5ptaHCS1v3-ViA0,8579
|
@@ -675,20 +690,20 @@ sglang/srt/models/minicpm3.py,sha256=6-gfHSfXwyB5zw7AIj-c5TzjpEKR6CM0H67MrD8LVUE
|
|
675
690
|
sglang/srt/models/minicpmo.py,sha256=st8I13Ere5RkRHHQQN1LgZh1ybUA3_buxaaE4XlV8ag,76123
|
676
691
|
sglang/srt/models/minicpmv.py,sha256=g4aAOG8PVGkZqGmlneVaScAtNpSLqSVbZGRAikyrBy8,30394
|
677
692
|
sglang/srt/models/mistral.py,sha256=ni7PppA_5X4ivTnIps3yoEaMEL-G6Gaf9b5hGC1vU5Q,3475
|
678
|
-
sglang/srt/models/mixtral.py,sha256=
|
693
|
+
sglang/srt/models/mixtral.py,sha256=OL7TOi6RmnBwfL6n9f5GZE1UI76IQ1QMYXc3X__zKJk,17307
|
679
694
|
sglang/srt/models/mixtral_quant.py,sha256=UUIq7lpUonD9IoGePyl59oJYEcVwT9wUXvtVp5tjQ9Y,15406
|
680
695
|
sglang/srt/models/mllama.py,sha256=OdX7brhyfGiMFPulxF77QOUi-Kcscg3Qo4ipyxzs9yA,39670
|
681
696
|
sglang/srt/models/mllama4.py,sha256=yt2YNE7S6buLAaqSfxD2LcJL1ZRzUzKWU21rCbzDzQo,20465
|
682
697
|
sglang/srt/models/olmo.py,sha256=7-q_fA6XXdG7kPUjpUzYkzMUWJobuSjhqjYw9xSUs_c,12671
|
683
698
|
sglang/srt/models/olmo2.py,sha256=azmljhJF4ivcQfUtfsAUxq3ducE4tRKTL6iwe0IKYMg,14327
|
684
|
-
sglang/srt/models/olmoe.py,sha256=
|
699
|
+
sglang/srt/models/olmoe.py,sha256=30HbQ35ELbJTwvD2fWezMoTt9zYYfsFDE5mxz4pDtgg,16129
|
685
700
|
sglang/srt/models/persimmon.py,sha256=86Duo3HiZqDj9O2UzWbJgUEhQOXzGBUdhUofQhcs1VE,11244
|
686
701
|
sglang/srt/models/phi.py,sha256=n6A1d47MvnR1lmSsZ3TuzXk5kT1Lntj_YQ5uNvR0s5o,10287
|
687
702
|
sglang/srt/models/phi3_small.py,sha256=eJb8aS_3KLObrq3PNkoIyVHaQ6SZTAJe42rbpC54QKg,16012
|
688
703
|
sglang/srt/models/phi4mm.py,sha256=Yh2GnrT8zyvOTMPslHbhUlNOTAzZ6LuzMNxKaJjr38c,21107
|
689
704
|
sglang/srt/models/phi4mm_audio.py,sha256=0ChekwoYudAnbY0-JyNwz_inzMlxM8FmULqR9mwkPhQ,48877
|
690
705
|
sglang/srt/models/phi4mm_utils.py,sha256=bW3un4x3SHDvSkAOHQEFO286FGdOPeKhBpJCOmNlC9E,66956
|
691
|
-
sglang/srt/models/phimoe.py,sha256=
|
706
|
+
sglang/srt/models/phimoe.py,sha256=EGaKFi02MZP20qFrILA4o2SJ0wb1HoJagFTSqVUbJcQ,19223
|
692
707
|
sglang/srt/models/pixtral.py,sha256=ZkZrV0mEfmbBdgRko2AvsMFZbAVskgp_5a5p1xCSRN0,16835
|
693
708
|
sglang/srt/models/qwen.py,sha256=j0OU3JjznWi_TbayI09yYGM-Obov6mQzJO82Hs0qBGw,11868
|
694
709
|
sglang/srt/models/qwen2.py,sha256=0gnggs2q-_FtD75J-UM4KMNBXSapVQGz73B-C2yZHDg,22437
|
@@ -705,6 +720,7 @@ sglang/srt/models/registry.py,sha256=bH9H0OiNV0Cn7FRBM30Oh6dxICTs9mJscdLtHYPJvxc
|
|
705
720
|
sglang/srt/models/roberta.py,sha256=3k53V2Gbezk3jU-D03thXx8csGn5DxFK01ZQ9WFiWPI,9828
|
706
721
|
sglang/srt/models/siglip.py,sha256=DIVJRwdtpLD2QT1kVPIHw7Bn9BE40xJbkHujDNzkjgA,9892
|
707
722
|
sglang/srt/models/stablelm.py,sha256=0x_31uIr3WcWwecdPAI3ek9KkyKBJS7VwknTk2y0gjY,12281
|
723
|
+
sglang/srt/models/step3_vl.py,sha256=SAOpDqs0n53iYNbLHf1t9vjEw2GilQctAM71-KCcp2Q,35128
|
708
724
|
sglang/srt/models/torch_native_llama.py,sha256=oTxxof5Wx2b2egIwWx56LeHjtPGQleQ2zM5jXHMiuOU,19293
|
709
725
|
sglang/srt/models/transformers.py,sha256=_CL0npi-_HvqzxkLgFhv2EE3bfGvCLXPYAtPFywZOr0,10260
|
710
726
|
sglang/srt/models/vila.py,sha256=3NiRHWOqXnCRjXmswAldsNtiE5zRILbScEsbhUzLZF4,9846
|
@@ -712,7 +728,7 @@ sglang/srt/models/xverse.py,sha256=DsNVI9JpzN4jj0Ry6aTrj7r-xq5YLOoDX2kH4YLJA-I,1
|
|
712
728
|
sglang/srt/models/xverse_moe.py,sha256=7KCM2-j12towDMNvXkuuYiBOmNauH6NG4Ip40x0khqA,16782
|
713
729
|
sglang/srt/models/yivl.py,sha256=oToK7-u5IGO7xwpJIQ7VtudlK6-zPqJX4bt6_wv0SH8,4850
|
714
730
|
sglang/srt/multimodal/mm_utils.py,sha256=6bV1_a7Iet9W0y3qdd0E-hFM78zalIzNZCYbLzJX2y8,12640
|
715
|
-
sglang/srt/multimodal/processors/base_processor.py,sha256=
|
731
|
+
sglang/srt/multimodal/processors/base_processor.py,sha256=VM2whACib10qNIB6k3EwRrHE0BpdE2tLFw_W-Tqj3yk,24198
|
716
732
|
sglang/srt/multimodal/processors/clip.py,sha256=5nXZuQYbyf-5mlqPwjhQrlWqxvswImWZQXivChsiHfQ,1057
|
717
733
|
sglang/srt/multimodal/processors/deepseek_vl_v2.py,sha256=Pymag9f0U5L_bBOTFs2q94BbuPJ-VwqSixs3meO0nsM,2569
|
718
734
|
sglang/srt/multimodal/processors/gemma3.py,sha256=7aD6cR60iSC_MqjzdCDMAgtrb_cmy9YJyqLgVRClBT8,1986
|
@@ -728,6 +744,7 @@ sglang/srt/multimodal/processors/phi4mm.py,sha256=8GaUVpGucV4UKoa0XkxN0gDpMZax6U
|
|
728
744
|
sglang/srt/multimodal/processors/pixtral.py,sha256=Lx5Z-9NkovLDTHlRBznHxGn4r2XhDz8am2XpOskOVQY,3203
|
729
745
|
sglang/srt/multimodal/processors/qwen_audio.py,sha256=jxtArfNuBH4q9LQVEydMDsj85avqBGNl-v1ZZTjC9E0,2367
|
730
746
|
sglang/srt/multimodal/processors/qwen_vl.py,sha256=tZOpz8dabyNvjS4hn0UxLf-EaEZH8kmHjyZaYRm9EZ8,10498
|
747
|
+
sglang/srt/multimodal/processors/step3_vl.py,sha256=JEHsj9SQw5udc3s-o1rwBF-WsrMTCxUcbgM4qFXKTT0,18240
|
731
748
|
sglang/srt/multimodal/processors/vila.py,sha256=vWgV1lTdjiFiTR8w-7fC66-L_tpOOD59c-c9NljGelE,2192
|
732
749
|
sglang/srt/sampling/custom_logit_processor.py,sha256=AwODYVJdRkcQ8PGtJrhzKsqAgn8XZLQbAmR9fGiQzmc,1608
|
733
750
|
sglang/srt/sampling/sampling_batch_info.py,sha256=Duk4Fp99QZyOFld3i4AGwkW9FlULY86CNKv6v0_kA4w,14683
|
@@ -741,7 +758,7 @@ sglang/srt/speculative/build_eagle_tree.py,sha256=O9LJNaBflgJdWT94D-rGH1gJFJ18ns
|
|
741
758
|
sglang/srt/speculative/eagle_draft_cuda_graph_runner.py,sha256=kVqMGj25jxtJlP-nTSlq_QJgoabFqKOU7-0WeUFhvw8,14509
|
742
759
|
sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py,sha256=hLjaD66K3ZE5SWsjvSiSdSexQ55F3EuSnfb4oe7rrSY,15261
|
743
760
|
sglang/srt/speculative/eagle_utils.py,sha256=x5MKA2GkecNAXE58KKhPJRy5KxCLhRkD-C_kVSZIyzc,46433
|
744
|
-
sglang/srt/speculative/eagle_worker.py,sha256=
|
761
|
+
sglang/srt/speculative/eagle_worker.py,sha256=AWMaTVgNgKmCecLsQRMLR5jIW6j69ogAQewYHrPK4d0,38717
|
745
762
|
sglang/srt/speculative/spec_info.py,sha256=rhaKG0TzyF9XZYHEWp1jccwTBohSNsUDvxHFtAoOl18,709
|
746
763
|
sglang/srt/weight_sync/utils.py,sha256=jpmfXtiCvUYpwWh4bMgQgv0JSulPi8TwIz4aTsxi0XU,4148
|
747
764
|
sglang/test/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
@@ -775,8 +792,9 @@ sglang/test/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
|
|
775
792
|
sglang/test/attention/test_flashattn_backend.py,sha256=_rTG849FwQdVTyGKkqhczaOqngBmRWXFmkl5NnuK1GM,13914
|
776
793
|
sglang/test/attention/test_flashattn_mla_backend.py,sha256=g4O50WblTpM7_Gq2b76k0i25_z01BOUBQ4i6PmyxpO4,10774
|
777
794
|
sglang/test/attention/test_prefix_chunk_info.py,sha256=hpoDe2wfSa6RlUbfyri_c0iyBTb35UXGL9I2Xh6jamM,7772
|
778
|
-
sglang
|
779
|
-
sglang-0.4.
|
780
|
-
sglang-0.4.
|
781
|
-
sglang-0.4.
|
782
|
-
sglang-0.4.
|
795
|
+
sglang/test/attention/test_trtllm_mla_backend.py,sha256=D7KOJbsfGRSdO5dMlGokBpiC6Sh42g51HlVkgxSK-yI,36251
|
796
|
+
sglang-0.4.10.post1.dist-info/licenses/LICENSE,sha256=FJXh51fvTQklojUFY89XVLsjxRcBqOxPs8XNy-2uZ0c,11346
|
797
|
+
sglang-0.4.10.post1.dist-info/METADATA,sha256=SWpzKC2hhUHjpZ9ZlfGfYDn8-P_qUeqwZU2kpZDnH_0,27394
|
798
|
+
sglang-0.4.10.post1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
799
|
+
sglang-0.4.10.post1.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
|
800
|
+
sglang-0.4.10.post1.dist-info/RECORD,,
|
File without changes
|
File without changes
|
File without changes
|