sglang 0.3.4.post1__py3-none-any.whl → 0.3.5__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.
Files changed (91) hide show
  1. sglang/api.py +1 -1
  2. sglang/bench_latency.py +3 -3
  3. sglang/bench_server_latency.py +2 -3
  4. sglang/bench_serving.py +92 -0
  5. sglang/global_config.py +9 -3
  6. sglang/lang/chat_template.py +50 -25
  7. sglang/lang/interpreter.py +9 -1
  8. sglang/lang/ir.py +11 -2
  9. sglang/launch_server.py +1 -1
  10. sglang/srt/configs/model_config.py +76 -15
  11. sglang/srt/constrained/__init__.py +18 -0
  12. sglang/srt/constrained/bnf_cache.py +61 -0
  13. sglang/srt/constrained/fsm_cache.py +10 -3
  14. sglang/srt/constrained/grammar.py +190 -0
  15. sglang/srt/hf_transformers_utils.py +20 -5
  16. sglang/srt/layers/attention/flashinfer_backend.py +5 -5
  17. sglang/srt/layers/attention/triton_ops/decode_attention.py +110 -30
  18. sglang/srt/layers/attention/triton_ops/prefill_attention.py +1 -1
  19. sglang/srt/layers/fused_moe/fused_moe.py +4 -3
  20. sglang/srt/layers/fused_moe/layer.py +28 -0
  21. sglang/srt/layers/logits_processor.py +5 -5
  22. sglang/srt/layers/quantization/base_config.py +16 -1
  23. sglang/srt/layers/rotary_embedding.py +15 -48
  24. sglang/srt/layers/sampler.py +51 -39
  25. sglang/srt/layers/vocab_parallel_embedding.py +486 -0
  26. sglang/srt/managers/data_parallel_controller.py +8 -7
  27. sglang/srt/managers/detokenizer_manager.py +11 -9
  28. sglang/srt/managers/image_processor.py +4 -3
  29. sglang/srt/managers/io_struct.py +80 -78
  30. sglang/srt/managers/schedule_batch.py +46 -52
  31. sglang/srt/managers/schedule_policy.py +24 -13
  32. sglang/srt/managers/scheduler.py +145 -82
  33. sglang/srt/managers/tokenizer_manager.py +236 -334
  34. sglang/srt/managers/tp_worker.py +5 -5
  35. sglang/srt/managers/tp_worker_overlap_thread.py +58 -21
  36. sglang/srt/mem_cache/flush_cache.py +1 -1
  37. sglang/srt/mem_cache/memory_pool.py +10 -3
  38. sglang/srt/model_executor/cuda_graph_runner.py +34 -23
  39. sglang/srt/model_executor/forward_batch_info.py +6 -9
  40. sglang/srt/model_executor/model_runner.py +10 -19
  41. sglang/srt/models/baichuan.py +4 -4
  42. sglang/srt/models/chatglm.py +4 -4
  43. sglang/srt/models/commandr.py +1 -1
  44. sglang/srt/models/dbrx.py +5 -5
  45. sglang/srt/models/deepseek.py +4 -4
  46. sglang/srt/models/deepseek_v2.py +4 -4
  47. sglang/srt/models/exaone.py +4 -4
  48. sglang/srt/models/gemma.py +1 -1
  49. sglang/srt/models/gemma2.py +1 -1
  50. sglang/srt/models/gpt2.py +287 -0
  51. sglang/srt/models/gpt_bigcode.py +1 -1
  52. sglang/srt/models/grok.py +4 -4
  53. sglang/srt/models/internlm2.py +4 -4
  54. sglang/srt/models/llama.py +15 -7
  55. sglang/srt/models/llama_embedding.py +2 -10
  56. sglang/srt/models/llama_reward.py +5 -0
  57. sglang/srt/models/minicpm.py +4 -4
  58. sglang/srt/models/minicpm3.py +4 -4
  59. sglang/srt/models/mixtral.py +7 -5
  60. sglang/srt/models/mixtral_quant.py +4 -4
  61. sglang/srt/models/mllama.py +5 -5
  62. sglang/srt/models/olmo.py +4 -4
  63. sglang/srt/models/olmoe.py +4 -4
  64. sglang/srt/models/qwen.py +4 -4
  65. sglang/srt/models/qwen2.py +4 -4
  66. sglang/srt/models/qwen2_moe.py +4 -4
  67. sglang/srt/models/qwen2_vl.py +4 -8
  68. sglang/srt/models/stablelm.py +4 -4
  69. sglang/srt/models/torch_native_llama.py +4 -4
  70. sglang/srt/models/xverse.py +4 -4
  71. sglang/srt/models/xverse_moe.py +4 -4
  72. sglang/srt/openai_api/adapter.py +52 -66
  73. sglang/srt/sampling/penaltylib/penalizers/min_new_tokens.py +6 -3
  74. sglang/srt/sampling/sampling_batch_info.py +7 -13
  75. sglang/srt/sampling/sampling_params.py +5 -7
  76. sglang/srt/server.py +41 -33
  77. sglang/srt/server_args.py +34 -5
  78. sglang/srt/utils.py +40 -56
  79. sglang/test/run_eval.py +2 -0
  80. sglang/test/runners.py +2 -1
  81. sglang/test/srt/sampling/penaltylib/utils.py +1 -0
  82. sglang/test/test_utils.py +151 -6
  83. sglang/utils.py +62 -1
  84. sglang/version.py +1 -1
  85. sglang-0.3.5.dist-info/METADATA +344 -0
  86. sglang-0.3.5.dist-info/RECORD +152 -0
  87. {sglang-0.3.4.post1.dist-info → sglang-0.3.5.dist-info}/WHEEL +1 -1
  88. sglang-0.3.4.post1.dist-info/METADATA +0 -900
  89. sglang-0.3.4.post1.dist-info/RECORD +0 -148
  90. {sglang-0.3.4.post1.dist-info → sglang-0.3.5.dist-info}/LICENSE +0 -0
  91. {sglang-0.3.4.post1.dist-info → sglang-0.3.5.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,344 @@
1
+ Metadata-Version: 2.1
2
+ Name: sglang
3
+ Version: 0.3.5
4
+ Summary: SGLang is yet another fast serving framework for large language models and vision language models.
5
+ License: Apache License
6
+ Version 2.0, January 2004
7
+ http://www.apache.org/licenses/
8
+
9
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
10
+
11
+ 1. Definitions.
12
+
13
+ "License" shall mean the terms and conditions for use, reproduction,
14
+ and distribution as defined by Sections 1 through 9 of this document.
15
+
16
+ "Licensor" shall mean the copyright owner or entity authorized by
17
+ the copyright owner that is granting the License.
18
+
19
+ "Legal Entity" shall mean the union of the acting entity and all
20
+ other entities that control, are controlled by, or are under common
21
+ control with that entity. For the purposes of this definition,
22
+ "control" means (i) the power, direct or indirect, to cause the
23
+ direction or management of such entity, whether by contract or
24
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
25
+ outstanding shares, or (iii) beneficial ownership of such entity.
26
+
27
+ "You" (or "Your") shall mean an individual or Legal Entity
28
+ exercising permissions granted by this License.
29
+
30
+ "Source" form shall mean the preferred form for making modifications,
31
+ including but not limited to software source code, documentation
32
+ source, and configuration files.
33
+
34
+ "Object" form shall mean any form resulting from mechanical
35
+ transformation or translation of a Source form, including but
36
+ not limited to compiled object code, generated documentation,
37
+ and conversions to other media types.
38
+
39
+ "Work" shall mean the work of authorship, whether in Source or
40
+ Object form, made available under the License, as indicated by a
41
+ copyright notice that is included in or attached to the work
42
+ (an example is provided in the Appendix below).
43
+
44
+ "Derivative Works" shall mean any work, whether in Source or Object
45
+ form, that is based on (or derived from) the Work and for which the
46
+ editorial revisions, annotations, elaborations, or other modifications
47
+ represent, as a whole, an original work of authorship. For the purposes
48
+ of this License, Derivative Works shall not include works that remain
49
+ separable from, or merely link (or bind by name) to the interfaces of,
50
+ the Work and Derivative Works thereof.
51
+
52
+ "Contribution" shall mean any work of authorship, including
53
+ the original version of the Work and any modifications or additions
54
+ to that Work or Derivative Works thereof, that is intentionally
55
+ submitted to Licensor for inclusion in the Work by the copyright owner
56
+ or by an individual or Legal Entity authorized to submit on behalf of
57
+ the copyright owner. For the purposes of this definition, "submitted"
58
+ means any form of electronic, verbal, or written communication sent
59
+ to the Licensor or its representatives, including but not limited to
60
+ communication on electronic mailing lists, source code control systems,
61
+ and issue tracking systems that are managed by, or on behalf of, the
62
+ Licensor for the purpose of discussing and improving the Work, but
63
+ excluding communication that is conspicuously marked or otherwise
64
+ designated in writing by the copyright owner as "Not a Contribution."
65
+
66
+ "Contributor" shall mean Licensor and any individual or Legal Entity
67
+ on behalf of whom a Contribution has been received by Licensor and
68
+ subsequently incorporated within the Work.
69
+
70
+ 2. Grant of Copyright License. Subject to the terms and conditions of
71
+ this License, each Contributor hereby grants to You a perpetual,
72
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
73
+ copyright license to reproduce, prepare Derivative Works of,
74
+ publicly display, publicly perform, sublicense, and distribute the
75
+ Work and such Derivative Works in Source or Object form.
76
+
77
+ 3. Grant of Patent License. Subject to the terms and conditions of
78
+ this License, each Contributor hereby grants to You a perpetual,
79
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
80
+ (except as stated in this section) patent license to make, have made,
81
+ use, offer to sell, sell, import, and otherwise transfer the Work,
82
+ where such license applies only to those patent claims licensable
83
+ by such Contributor that are necessarily infringed by their
84
+ Contribution(s) alone or by combination of their Contribution(s)
85
+ with the Work to which such Contribution(s) was submitted. If You
86
+ institute patent litigation against any entity (including a
87
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
88
+ or a Contribution incorporated within the Work constitutes direct
89
+ or contributory patent infringement, then any patent licenses
90
+ granted to You under this License for that Work shall terminate
91
+ as of the date such litigation is filed.
92
+
93
+ 4. Redistribution. You may reproduce and distribute copies of the
94
+ Work or Derivative Works thereof in any medium, with or without
95
+ modifications, and in Source or Object form, provided that You
96
+ meet the following conditions:
97
+
98
+ (a) You must give any other recipients of the Work or
99
+ Derivative Works a copy of this License; and
100
+
101
+ (b) You must cause any modified files to carry prominent notices
102
+ stating that You changed the files; and
103
+
104
+ (c) You must retain, in the Source form of any Derivative Works
105
+ that You distribute, all copyright, patent, trademark, and
106
+ attribution notices from the Source form of the Work,
107
+ excluding those notices that do not pertain to any part of
108
+ the Derivative Works; and
109
+
110
+ (d) If the Work includes a "NOTICE" text file as part of its
111
+ distribution, then any Derivative Works that You distribute must
112
+ include a readable copy of the attribution notices contained
113
+ within such NOTICE file, excluding those notices that do not
114
+ pertain to any part of the Derivative Works, in at least one
115
+ of the following places: within a NOTICE text file distributed
116
+ as part of the Derivative Works; within the Source form or
117
+ documentation, if provided along with the Derivative Works; or,
118
+ within a display generated by the Derivative Works, if and
119
+ wherever such third-party notices normally appear. The contents
120
+ of the NOTICE file are for informational purposes only and
121
+ do not modify the License. You may add Your own attribution
122
+ notices within Derivative Works that You distribute, alongside
123
+ or as an addendum to the NOTICE text from the Work, provided
124
+ that such additional attribution notices cannot be construed
125
+ as modifying the License.
126
+
127
+ You may add Your own copyright statement to Your modifications and
128
+ may provide additional or different license terms and conditions
129
+ for use, reproduction, or distribution of Your modifications, or
130
+ for any such Derivative Works as a whole, provided Your use,
131
+ reproduction, and distribution of the Work otherwise complies with
132
+ the conditions stated in this License.
133
+
134
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
135
+ any Contribution intentionally submitted for inclusion in the Work
136
+ by You to the Licensor shall be under the terms and conditions of
137
+ this License, without any additional terms or conditions.
138
+ Notwithstanding the above, nothing herein shall supersede or modify
139
+ the terms of any separate license agreement you may have executed
140
+ with Licensor regarding such Contributions.
141
+
142
+ 6. Trademarks. This License does not grant permission to use the trade
143
+ names, trademarks, service marks, or product names of the Licensor,
144
+ except as required for reasonable and customary use in describing the
145
+ origin of the Work and reproducing the content of the NOTICE file.
146
+
147
+ 7. Disclaimer of Warranty. Unless required by applicable law or
148
+ agreed to in writing, Licensor provides the Work (and each
149
+ Contributor provides its Contributions) on an "AS IS" BASIS,
150
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
151
+ implied, including, without limitation, any warranties or conditions
152
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
153
+ PARTICULAR PURPOSE. You are solely responsible for determining the
154
+ appropriateness of using or redistributing the Work and assume any
155
+ risks associated with Your exercise of permissions under this License.
156
+
157
+ 8. Limitation of Liability. In no event and under no legal theory,
158
+ whether in tort (including negligence), contract, or otherwise,
159
+ unless required by applicable law (such as deliberate and grossly
160
+ negligent acts) or agreed to in writing, shall any Contributor be
161
+ liable to You for damages, including any direct, indirect, special,
162
+ incidental, or consequential damages of any character arising as a
163
+ result of this License or out of the use or inability to use the
164
+ Work (including but not limited to damages for loss of goodwill,
165
+ work stoppage, computer failure or malfunction, or any and all
166
+ other commercial damages or losses), even if such Contributor
167
+ has been advised of the possibility of such damages.
168
+
169
+ 9. Accepting Warranty or Additional Liability. While redistributing
170
+ the Work or Derivative Works thereof, You may choose to offer,
171
+ and charge a fee for, acceptance of support, warranty, indemnity,
172
+ or other liability obligations and/or rights consistent with this
173
+ License. However, in accepting such obligations, You may act only
174
+ on Your own behalf and on Your sole responsibility, not on behalf
175
+ of any other Contributor, and only if You agree to indemnify,
176
+ defend, and hold each Contributor harmless for any liability
177
+ incurred by, or claims asserted against, such Contributor by reason
178
+ of your accepting any such warranty or additional liability.
179
+
180
+ END OF TERMS AND CONDITIONS
181
+
182
+ APPENDIX: How to apply the Apache License to your work.
183
+
184
+ To apply the Apache License to your work, attach the following
185
+ boilerplate notice, with the fields enclosed by brackets "[]"
186
+ replaced with your own identifying information. (Don't include
187
+ the brackets!) The text should be enclosed in the appropriate
188
+ comment syntax for the file format. We also recommend that a
189
+ file or class name and description of purpose be included on the
190
+ same "printed page" as the copyright notice for easier
191
+ identification within third-party archives.
192
+
193
+ Copyright [yyyy] [name of copyright owner]
194
+
195
+ Licensed under the Apache License, Version 2.0 (the "License");
196
+ you may not use this file except in compliance with the License.
197
+ You may obtain a copy of the License at
198
+
199
+ http://www.apache.org/licenses/LICENSE-2.0
200
+
201
+ Unless required by applicable law or agreed to in writing, software
202
+ distributed under the License is distributed on an "AS IS" BASIS,
203
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
204
+ See the License for the specific language governing permissions and
205
+ limitations under the License.
206
+
207
+ Project-URL: Homepage, https://github.com/sgl-project/sglang
208
+ Project-URL: Bug Tracker, https://github.com/sgl-project/sglang/issues
209
+ Classifier: Programming Language :: Python :: 3
210
+ Classifier: License :: OSI Approved :: Apache Software License
211
+ Requires-Python: >=3.8
212
+ Description-Content-Type: text/markdown
213
+ License-File: LICENSE
214
+ Requires-Dist: requests
215
+ Requires-Dist: tqdm
216
+ Requires-Dist: numpy
217
+ Requires-Dist: IPython
218
+ Provides-Extra: all
219
+ Requires-Dist: sglang[srt]; extra == "all"
220
+ Requires-Dist: sglang[openai]; extra == "all"
221
+ Requires-Dist: sglang[anthropic]; extra == "all"
222
+ Requires-Dist: sglang[litellm]; extra == "all"
223
+ Provides-Extra: all_hip
224
+ Requires-Dist: sglang[srt_hip]; extra == "all-hip"
225
+ Requires-Dist: sglang[openai]; extra == "all-hip"
226
+ Requires-Dist: sglang[anthropic]; extra == "all-hip"
227
+ Requires-Dist: sglang[litellm]; extra == "all-hip"
228
+ Provides-Extra: all_xpu
229
+ Requires-Dist: sglang[srt_xpu]; extra == "all-xpu"
230
+ Requires-Dist: sglang[openai]; extra == "all-xpu"
231
+ Requires-Dist: sglang[anthropic]; extra == "all-xpu"
232
+ Requires-Dist: sglang[litellm]; extra == "all-xpu"
233
+ Provides-Extra: anthropic
234
+ Requires-Dist: anthropic>=0.20.0; extra == "anthropic"
235
+ Provides-Extra: dev
236
+ Requires-Dist: sglang[all]; extra == "dev"
237
+ Requires-Dist: sglang[test]; extra == "dev"
238
+ Provides-Extra: dev_hip
239
+ Requires-Dist: sglang[all_hip]; extra == "dev-hip"
240
+ Requires-Dist: sglang[test]; extra == "dev-hip"
241
+ Provides-Extra: dev_xpu
242
+ Requires-Dist: sglang[all_xpu]; extra == "dev-xpu"
243
+ Requires-Dist: sglang[test]; extra == "dev-xpu"
244
+ Provides-Extra: litellm
245
+ Requires-Dist: litellm>=1.0.0; extra == "litellm"
246
+ Provides-Extra: openai
247
+ Requires-Dist: openai>=1.0; extra == "openai"
248
+ Requires-Dist: tiktoken; extra == "openai"
249
+ Provides-Extra: runtime_common
250
+ Requires-Dist: aiohttp; extra == "runtime-common"
251
+ Requires-Dist: decord; extra == "runtime-common"
252
+ Requires-Dist: fastapi; extra == "runtime-common"
253
+ Requires-Dist: hf-transfer; extra == "runtime-common"
254
+ Requires-Dist: huggingface-hub; extra == "runtime-common"
255
+ Requires-Dist: interegular; extra == "runtime-common"
256
+ Requires-Dist: orjson; extra == "runtime-common"
257
+ Requires-Dist: packaging; extra == "runtime-common"
258
+ Requires-Dist: pillow; extra == "runtime-common"
259
+ Requires-Dist: psutil; extra == "runtime-common"
260
+ Requires-Dist: pydantic; extra == "runtime-common"
261
+ Requires-Dist: python-multipart; extra == "runtime-common"
262
+ Requires-Dist: torchao; extra == "runtime-common"
263
+ Requires-Dist: uvicorn; extra == "runtime-common"
264
+ Requires-Dist: uvloop; extra == "runtime-common"
265
+ Requires-Dist: zmq; extra == "runtime-common"
266
+ Requires-Dist: outlines>=0.0.44; extra == "runtime-common"
267
+ Requires-Dist: modelscope; extra == "runtime-common"
268
+ Provides-Extra: srt
269
+ Requires-Dist: sglang[runtime_common]; extra == "srt"
270
+ Requires-Dist: torch; extra == "srt"
271
+ Requires-Dist: vllm==0.6.3.post1; extra == "srt"
272
+ Provides-Extra: srt_hip
273
+ Requires-Dist: sglang[runtime_common]; extra == "srt-hip"
274
+ Requires-Dist: torch; extra == "srt-hip"
275
+ Requires-Dist: vllm==0.6.3.dev13; extra == "srt-hip"
276
+ Provides-Extra: srt_xpu
277
+ Requires-Dist: sglang[runtime_common]; extra == "srt-xpu"
278
+ Provides-Extra: test
279
+ Requires-Dist: jsonlines; extra == "test"
280
+ Requires-Dist: matplotlib; extra == "test"
281
+ Requires-Dist: pandas; extra == "test"
282
+ Requires-Dist: sentence-transformers; extra == "test"
283
+ Requires-Dist: accelerate; extra == "test"
284
+ Requires-Dist: peft; extra == "test"
285
+
286
+ <div align="center" id="sglangtop">
287
+ <img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400" margin="10px"></img>
288
+
289
+ [![PyPI](https://img.shields.io/pypi/v/sglang)](https://pypi.org/project/sglang)
290
+ ![PyPI - Downloads](https://img.shields.io/pypi/dm/sglang)
291
+ [![license](https://img.shields.io/github/license/sgl-project/sglang.svg)](https://github.com/sgl-project/sglang/tree/main/LICENSE)
292
+ [![issue resolution](https://img.shields.io/github/issues-closed-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)
293
+ [![open issues](https://img.shields.io/github/issues-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)
294
+
295
+ </div>
296
+
297
+ --------------------------------------------------------------------------------
298
+
299
+ | [**Blog**](https://lmsys.org/blog/2024-07-25-sglang-llama3/) | [**Documentation**](https://sgl-project.github.io/) | [**Join Slack**](https://join.slack.com/t/sgl-fru7574/shared_invite/zt-2ngly9muu-t37XiH87qvD~6rVBTkTEHw) |
300
+ [**Join Bi-Weekly Development Meeting**](https://docs.google.com/document/d/1xEow4eIM152xNcRxqZz9VEcOiTQo8-CEuuQ5qTmkt-E/edit?usp=sharing) |
301
+
302
+ ## News
303
+ - [2024/10] 🔥 The First SGLang Online Meetup ([slides](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#the-first-sglang-online-meetup)).
304
+ - [2024/09] SGLang v0.3 Release: 7x Faster DeepSeek MLA, 1.5x Faster torch.compile, Multi-Image/Video LLaVA-OneVision ([blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)).
305
+ - [2024/07] Faster Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM) ([blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/)).
306
+
307
+ <details>
308
+ <summary>More</summary>
309
+
310
+ - [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
311
+ - [2024/04] SGLang is used by the official **LLaVA-NeXT (video)** release ([blog](https://llava-vl.github.io/blog/2024-04-30-llava-next-video/)).
312
+ - [2024/01] SGLang provides up to **5x faster inference** with RadixAttention ([blog](https://lmsys.org/blog/2024-01-17-sglang/)).
313
+ - [2024/01] SGLang powers the serving of the official **LLaVA v1.6** release demo ([usage](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file#demo)).
314
+
315
+ </details>
316
+
317
+ ## About
318
+ SGLang is a fast serving framework for large language models and vision language models.
319
+ It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language.
320
+ The core features include:
321
+
322
+ - **Fast Backend Runtime**: Provides efficient serving with RadixAttention for prefix caching, jump-forward constrained decoding, continuous batching, token attention (paged attention), tensor parallelism, FlashInfer kernels, chunked prefill, and quantization (INT4/FP8/AWQ/GPTQ).
323
+ - **Flexible Frontend Language**: Offers an intuitive interface for programming LLM applications, including chained generation calls, advanced prompting, control flow, multi-modal inputs, parallelism, and external interactions.
324
+ - **Extensive Model Support**: Supports a wide range of generative models (Llama, Gemma, Mistral, QWen, DeepSeek, LLaVA, etc.) and embedding models (e5-mistral), with easy extensibility for integrating new models.
325
+ - **Active Community**: SGLang is open-source and backed by an active community with industry adoption.
326
+
327
+ ## Install
328
+ See [https://sgl-project.github.io/start/install.html](https://sgl-project.github.io/start/install.html)
329
+
330
+ ## Backend: SGLang Runtime (SRT)
331
+ See [https://sgl-project.github.io/backend/backend.html](https://sgl-project.github.io/backend/backend.html)
332
+
333
+ ## Frontend: Structured Generation Language (SGLang)
334
+ See [https://sgl-project.github.io/frontend/frontend.html](https://sgl-project.github.io/frontend/frontend.html)
335
+
336
+ ## Benchmark And Performance
337
+ Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3 blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)
338
+
339
+ ## Roadmap
340
+ [Development Roadmap (2024 Q4)](https://github.com/sgl-project/sglang/issues/1487)
341
+
342
+ ## Citation And Acknowledgment
343
+ Please cite our paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.
344
+ We also learned from the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).
@@ -0,0 +1,152 @@
1
+ sglang/__init__.py,sha256=b_pqO9bR2fjK9En_tigfzKTiQzE8b_hUizY0DAKVk1M,1616
2
+ sglang/api.py,sha256=3I9YUJNOeCqwKymZec2JR_agjTyKIx4XoT6IGdZ4_Cs,6953
3
+ sglang/bench_latency.py,sha256=SSqZjcCNO88ExpT94qBZ5CmuA5o0T8wMTBnxLsNMqik,18259
4
+ sglang/bench_server_latency.py,sha256=N1MODIzcMk74yOWmY19d36aih3ewtHOemLxoieKtdhw,5866
5
+ sglang/bench_serving.py,sha256=0RR0RsrQqLWqcIPENfrS97F9HJiVXIZvGOWy4R2GvDA,43680
6
+ sglang/check_env.py,sha256=rGRABCgt-0SfUrow4px28b2P59aMn8eVTnN5eZc_a8s,5397
7
+ sglang/global_config.py,sha256=fnT0U9vlHdGaQFKN9tYTnUF4-eVW4HYQURd5zvPtrg0,1286
8
+ sglang/launch_server.py,sha256=_XIqBcXArYtHTqilOFkYWKZBYXGCMHAxbYOST08LGj0,415
9
+ sglang/launch_server_llavavid.py,sha256=tGc17S1vUfLwbi1GB26oOdXxTWr7gjlqpTrPnrMRNO8,1007
10
+ sglang/utils.py,sha256=73tkeT4gDzmVkWO4nVXQHS9XlzH7CSL-I_uRpEDsCPg,11546
11
+ sglang/version.py,sha256=ThnCuF3X7rsQSd5PAea_jfYA70ZmhLvkFcLBxBPwZnY,22
12
+ sglang/lang/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
13
+ sglang/lang/chat_template.py,sha256=jprS3-In2FTUoedKwZg-HYvDwU8RTIYntOlf2zoN2sU,14814
14
+ sglang/lang/choices.py,sha256=-W1DVw9N9ZliVpvmWrzIXG4cswAah8eMQrHWzkS3D8o,6234
15
+ sglang/lang/compiler.py,sha256=o1C6G3TzhjSlsH-doTPy5oiVehr57dxNTa5oZw5TTAI,7639
16
+ sglang/lang/interpreter.py,sha256=SBjejhLhTKzNM0HbjtTg5r17WPJ64WFSk6lcM_SCWKs,30717
17
+ sglang/lang/ir.py,sha256=zpzzAO1YVldhE95Vwz5hU_TQltu-xt8A6rfFr0PuIDA,18410
18
+ sglang/lang/tracer.py,sha256=borJmlSJOhg1RUndGRnilnR60eEZz2Y9aU7BpftsOxU,8287
19
+ sglang/lang/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
20
+ sglang/lang/backend/anthropic.py,sha256=EXRX7xJgA5KZszX7toSLVnKzFQ5EO0Loj-YjHFtxSxg,2081
21
+ sglang/lang/backend/base_backend.py,sha256=Q5HdiDtyBewQeoYH0kDtBRVL8KFiEPNq9dw7XmauHQ8,1985
22
+ sglang/lang/backend/litellm.py,sha256=ugmL7sfUxkUHVbHtwNzHgdQAEd4UCjNQboFuE3KThcY,2450
23
+ sglang/lang/backend/openai.py,sha256=qM7eVH_kMxnDd2rpxOH0v76KxtOJFlAwgLgWIKvFGCI,15060
24
+ sglang/lang/backend/runtime_endpoint.py,sha256=iVb7SlrpJ1ic92QG5kQUphZUb2EaVWY43dkmAO5pju4,10514
25
+ sglang/lang/backend/vertexai.py,sha256=O-iBLD-y3vq80UxnrAoJri7bxpgd-_eakZ88Cf8bEGA,4855
26
+ sglang/srt/conversation.py,sha256=erz6wEXMcSmBlskuUhX2c-MT0EMyqyFpTem9PgastEE,21107
27
+ sglang/srt/hf_transformers_utils.py,sha256=QbYVTnz0UdaXESPMAaq1OMzzznn95J_l08eXJuB68aU,6618
28
+ sglang/srt/mm_utils.py,sha256=zox644S3IHUWmADdK4MnIbdTS2DWHOy0_Dq0gCU38QQ,12273
29
+ sglang/srt/server.py,sha256=4yKD85OlhhkneF7VOzWZMro0P8n1xdKgnZfCWdjrXao,27502
30
+ sglang/srt/server_args.py,sha256=AfbBXcrC_XpTWOoZcace0iRksKwyh8-NS1E7RMTWM5A,28912
31
+ sglang/srt/utils.py,sha256=zdoZlo0_R18mAWFc4tYnkxVb7qhqcCTKovaEn2dAHLw,23121
32
+ sglang/srt/configs/__init__.py,sha256=_usVIXHQjft4PAJ1Y-yGQOn2QNOv501GYMlQwpGXbns,208
33
+ sglang/srt/configs/exaone.py,sha256=Duxd4yQoKy8GWEzZD_kCY_OzmN_67CTJL_Kgn0eXk3g,10731
34
+ sglang/srt/configs/model_config.py,sha256=bxG-vD8ZmXbypKW6Hvz8AS7rcwjTxt0TzG7p59m3t2E,9387
35
+ sglang/srt/configs/qwen2vl.py,sha256=AYHuFgJ0bwhWYkD7S6fvP7yJejJnuhy4xp5Q2W-O6ps,4424
36
+ sglang/srt/constrained/__init__.py,sha256=VXEY9K8HrEBv6QHe3X7J5ingiDugSF9_cpEbEcpBId4,2466
37
+ sglang/srt/constrained/base_tool_cache.py,sha256=5sazBMHHDpHMoqOjuY6itCxwTmIFCflIWEDXMtmrPVs,2006
38
+ sglang/srt/constrained/bnf_cache.py,sha256=c8msJ57Gj7aMy1ccTRERLgVuovEeDJx-wVPOhYF0w9k,2057
39
+ sglang/srt/constrained/fsm_cache.py,sha256=CWwtOHTU3sHmw71OhWxl05YgU7cNNVWohlUt71rG230,3536
40
+ sglang/srt/constrained/grammar.py,sha256=kvfyP2E53xo8jVWVZ_qHlJn0U4Qi2WaNi2yMZPKgI_0,6952
41
+ sglang/srt/constrained/jump_forward.py,sha256=o-CzJu3DEs0eFKlLzsQVYMSo4vBKpffs25sXLOJd6jc,6997
42
+ sglang/srt/layers/activation.py,sha256=7VEkCrx2dvl629Lz0fkJcJfVoZA-ykEdkpTzKEc_drQ,5225
43
+ sglang/srt/layers/layernorm.py,sha256=HCj8Y_X6MNNdtQU2sWKgyjIqVERxl9dqrmjbBbyJjpE,3796
44
+ sglang/srt/layers/linear.py,sha256=EOdlpAf6srqxzvPpxcv10KFJKedNc22CGP1qEvpRbDg,46131
45
+ sglang/srt/layers/logits_processor.py,sha256=1l-hJoeZUfrPPmCWcyscl0ThgKWpprUELiL1mVDfbPE,12556
46
+ sglang/srt/layers/pooler.py,sha256=rj2lygvleBnyLCBZ8I11HGMgpfIDsT0l3PIkshJwdu4,1606
47
+ sglang/srt/layers/radix_attention.py,sha256=i07VRXPDHj-zJ1TSrXEqCxumQwYSHwAvc8DoIg-Irtg,1964
48
+ sglang/srt/layers/rotary_embedding.py,sha256=gfRKBB8FmsQKiDH0Crh_KRIGRUuvEgazH1p_n9D_m7E,3889
49
+ sglang/srt/layers/sampler.py,sha256=3zfth1Kz24X4sUq7Z_cjZwHgPVivI-rgPtIeUbsiiWU,4589
50
+ sglang/srt/layers/torchao_utils.py,sha256=1nzZkSzbF4qCAMeBKAeeDpMl_mK8imiY2RL3xFEgvAw,3340
51
+ sglang/srt/layers/vocab_parallel_embedding.py,sha256=8Tx0WUNibDoNkGruGzRIkvp6t7D54e-nchdezeQ5Nzk,22302
52
+ sglang/srt/layers/attention/__init__.py,sha256=EL1o6Q5vLgViN3pOr2A7F6K9FlNEpMdBypFAVMeq_HA,2445
53
+ sglang/srt/layers/attention/double_sparsity_backend.py,sha256=BlX7uXteQpnoOnKsdBKh8h20zMVMEiibB5F_PkZSlNI,10706
54
+ sglang/srt/layers/attention/flashinfer_backend.py,sha256=843CbZsRfzWp5FTusNXXL1o4N3jd0hoCNpsoUR6Qjxk,23306
55
+ sglang/srt/layers/attention/triton_backend.py,sha256=DKUEzxQE8iBvJPNHmQwP1pyx2wXmSsLqzBhLjJznIUk,6482
56
+ sglang/srt/layers/attention/triton_ops/decode_attention.py,sha256=7cDNPMMkz7--ebNKUeSaLY_6hBbvr_NqDodYFtW9ahA,18433
57
+ sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py,sha256=1pSXfY3EEaM7iRN_uElHnAfsrJMhTFbu9fj8Z0O2PbE,21480
58
+ sglang/srt/layers/attention/triton_ops/extend_attention.py,sha256=nEG7iBh1pAy3WaqPdLZwCJwDgyk5HLQ181kBS2nxbwg,11179
59
+ sglang/srt/layers/attention/triton_ops/prefill_attention.py,sha256=LnuWqGAba03e25adxS_lFgjTV6nBWsVBUGUvrl-8alQ,5993
60
+ sglang/srt/layers/fused_moe/__init__.py,sha256=bWCrDdOy2ANEXTb8CHYO63O3Iu3eZnn0PJbgl0z5vvE,75
61
+ sglang/srt/layers/fused_moe/fused_moe.py,sha256=uRmDUleTaJKBbsTfum6RgHifUbgi6yKuB2dw_mIhw3M,23250
62
+ sglang/srt/layers/fused_moe/layer.py,sha256=tbHnUJs3uvdDsl3VnwtyGA31VtFouNTPD7h7fPSCYOc,23613
63
+ sglang/srt/layers/fused_moe/patch.py,sha256=B9cDtHqHfnWE0QqZAffvUi6cVRKcMBMKDGJWGIaKh3U,3898
64
+ sglang/srt/layers/quantization/__init__.py,sha256=QilMNqgu3eOFUkEjXLSDa1NvoNdi_CAvC8a1hprOgN8,2979
65
+ sglang/srt/layers/quantization/base_config.py,sha256=fx-FeA1a4jg7HDoYvIKC5G_wLcfeOOyIJQ6MtCaHpZ4,4664
66
+ sglang/srt/lora/lora.py,sha256=meRL7oBUx8mxV_isc3Lp0EIsFQWC2PvaN-fE78BmMwg,14970
67
+ sglang/srt/lora/lora_config.py,sha256=paVB7F7SIuxr_vodvKf8zzAlH2fdVYHhXxcXV62D0Vo,1411
68
+ sglang/srt/lora/lora_manager.py,sha256=gzBwYXZEPYj56PkGTshTbWRfl_370wb6uTcRhDaLiF8,12801
69
+ sglang/srt/managers/data_parallel_controller.py,sha256=_XB6Ianc8TiqwLTW-7DH6gGjVYBeBU_6WjjaDk0snIY,5686
70
+ sglang/srt/managers/detokenizer_manager.py,sha256=pBCcK-wKgPk4Ty-vQFSGovEZEE_yKK1f7YVDW8vDcYw,7962
71
+ sglang/srt/managers/image_processor.py,sha256=Pk_dtXzljTkFt7Acsv1RyDzEqvCvjc7BMngxGhtkpDU,13817
72
+ sglang/srt/managers/io_struct.py,sha256=23-eJQrpMw7OJ0LiDvBVKpI36rdyxJluFlHJ7wXjKqw,12261
73
+ sglang/srt/managers/schedule_batch.py,sha256=LIkxGNZC_PWIX7-BJGLRpzgNIGH-1ZxL9RUZE-dgo70,39653
74
+ sglang/srt/managers/schedule_policy.py,sha256=LH0rh1PiI5LK-dSd3dar8_po6FidiBUuj0Xcp_yNQAA,12295
75
+ sglang/srt/managers/scheduler.py,sha256=p72s46nNnUl5YTKfgwRNmcc8NZbBSGudYuqOP2bZsyc,45524
76
+ sglang/srt/managers/tokenizer_manager.py,sha256=fGVMxJb-UQPokqdlbphWHSVnLyKWAY8JK7fHe6iVa2I,21793
77
+ sglang/srt/managers/tp_worker.py,sha256=S5oim5xrkg1j68hYq6LfC8T533JYmQX9Kabt6U8ZXn4,5726
78
+ sglang/srt/managers/tp_worker_overlap_thread.py,sha256=j5J4yHyR7w2HgAbN7S__299ADvsoyap5HK63SWMNavQ,7546
79
+ sglang/srt/mem_cache/base_prefix_cache.py,sha256=qEQwEkG4E5rab2ZoTqcesf5pR_J4nV2jBxIHsBJHtIM,924
80
+ sglang/srt/mem_cache/chunk_cache.py,sha256=VcCpyrf5FOQ5xoKeOouCI5ZQLkZo_pgY1SPbDDkagGg,2492
81
+ sglang/srt/mem_cache/flush_cache.py,sha256=GYcxmNXh4hsMpFfNOuCTpKilW7guZwTtAg_usVeM3J0,979
82
+ sglang/srt/mem_cache/memory_pool.py,sha256=41fjuj_sD0yfJq-sy-X99cc2djBa6w4dy2y47V0WqNU,10934
83
+ sglang/srt/mem_cache/radix_cache.py,sha256=DzLCO_gYQ7X_C2NJSEHzzMZhb5HzWjKF9wXJQsnzr8M,10427
84
+ sglang/srt/model_executor/cuda_graph_runner.py,sha256=zRxXxV54b4SUXk9BQ1zPAS2VXCBRBvT15A64Yf0kBSE,12909
85
+ sglang/srt/model_executor/forward_batch_info.py,sha256=1GM6A-tqTDD0MEMQx93PC7XahABr0vlv7JBXohaehkc,9272
86
+ sglang/srt/model_executor/model_runner.py,sha256=Zs-u9sJREJD-1omhaFjBYfgR_2_7Cj0O5mGgQ0NtR8s,26793
87
+ sglang/srt/models/baichuan.py,sha256=RyvPQvi7wy9VUGvLwG17XttcTp43yRj6c3zNRImBToA,15005
88
+ sglang/srt/models/chatglm.py,sha256=9hCXTqGX8DMvSPSn6wlK0YNNRWGS4UiS4-xjFsO9hYU,13135
89
+ sglang/srt/models/commandr.py,sha256=leoQNn4VRqa9SXos6DcrkHVG6-Xp-kjBn2PUgqc9bs8,14051
90
+ sglang/srt/models/dbrx.py,sha256=IiVIk_rVd0RlvfIJGIThPOPkoYT3U649PrduThiKRzg,14545
91
+ sglang/srt/models/deepseek.py,sha256=DjW2B21isWE6A2C8A3VGZ-G0k1DkhWHO3dZZjcOVG50,15828
92
+ sglang/srt/models/deepseek_v2.py,sha256=z6532MRN1tBltFNteFJfimnaGpyNmK6g_sdNmTzsVmk,28230
93
+ sglang/srt/models/exaone.py,sha256=YMyH4zxyCaCB432vCcom800efPI19_vIQ3OXLkLiXxk,12984
94
+ sglang/srt/models/gemma.py,sha256=D_zjG312BeOPeplGzo5Z8tSMH9xL7wZ4KIgczZ9yJ0E,12193
95
+ sglang/srt/models/gemma2.py,sha256=iE56CYzPn-QCis4kcU7Yi0jvJ04KeU2deuZH2DaS2lM,14768
96
+ sglang/srt/models/gpt2.py,sha256=xWqU66KO6rNBnzA6uOBrlLWnwVzLKuC4UWHc5WuEHw8,10151
97
+ sglang/srt/models/gpt_bigcode.py,sha256=f6vvxBFPhV6GIZrOEKjJPu41TyVYw5Knq4h9WDvyEeY,10040
98
+ sglang/srt/models/grok.py,sha256=iSkvt7whYyMndUHBekM4vKHaDXnnmeJMErkklGpz624,14826
99
+ sglang/srt/models/internlm2.py,sha256=HOVOXz3b7eLF2wpG_FEK5PYnYOEpHPGJ0pufvL7HPD0,12099
100
+ sglang/srt/models/llama.py,sha256=X_LKJ02ofDfpgVVFexf_C6g4FikadfMikhuRVAuLN5I,16094
101
+ sglang/srt/models/llama_classification.py,sha256=WcHYFez7qloTCpXLy1A6-dBGHWp22ebv6yG68jFVBjc,3318
102
+ sglang/srt/models/llama_embedding.py,sha256=2ex2jrz31osaAd9V8sJeN0qyxmk-L5NgOBkXL1puGhI,3166
103
+ sglang/srt/models/llama_reward.py,sha256=48J6PmZJRFRv-6mEF6y5fxNKtRRZVQzvJqg3XaWDWa0,5448
104
+ sglang/srt/models/llava.py,sha256=ny3sK2sgYwrEhawSAc1tZeltcgukphSTdxsqyq-Epkc,24857
105
+ sglang/srt/models/llavavid.py,sha256=ztS5He-NF4fmfujdoMnKljOG1fNfPvp-6bduT7B6EMU,12137
106
+ sglang/srt/models/minicpm.py,sha256=hAzgBImQ1xDeRdaQt5hKcLl1h1T-1QFSerG2MOlLjt8,13722
107
+ sglang/srt/models/minicpm3.py,sha256=O6092exfoq8iHLmyfpVCubyQEzcfp4SmqtZJs7x4A8s,25014
108
+ sglang/srt/models/mistral.py,sha256=tiYoKjyYVzlQl52QUZ33odD2yCxj9dxcqln474VuZOw,744
109
+ sglang/srt/models/mixtral.py,sha256=b6AqEgL4y9wQpKKAGnhgzBtUypYo3dca5UOpGNLEt_A,13949
110
+ sglang/srt/models/mixtral_quant.py,sha256=2ND-aOHjcyeQMUvqLLqhXwOdlR_bEftMFk3hc3lnpvc,13969
111
+ sglang/srt/models/mllama.py,sha256=pET1x8wY04yoS8HMCncKx0tFPqGp78K8rlA7Eq7XioE,37889
112
+ sglang/srt/models/olmo.py,sha256=eWPmo5AAnBhNGdMwklh1of3JnRzAszgQp4opeiiYidI,11887
113
+ sglang/srt/models/olmoe.py,sha256=fEWr-RmW6l6fVA8jM9KX8bumUWLNQQG8VxGpajlkhUs,15242
114
+ sglang/srt/models/qwen.py,sha256=vQoq8Bv8A2zc-LE1i-E97A8i4ydtfxb2yt2JG6Tp9PQ,9851
115
+ sglang/srt/models/qwen2.py,sha256=Y1f_PxZMTkSLgENbKl96VfNGBfvcU4cljpVe1a3vzVg,12328
116
+ sglang/srt/models/qwen2_moe.py,sha256=RRuHLN1fIYFS4du4pUPNzGL-Rt2wLrjlgDfXiczZQ5c,16975
117
+ sglang/srt/models/qwen2_vl.py,sha256=scKzs-KTI64CRRcBNWQniXURLO3WiJEzx-MsisH1Als,26093
118
+ sglang/srt/models/stablelm.py,sha256=rIQOv9OS_Vb2nOT_AMx0yGG2onwmCbbxvXL_SPdZX7k,11256
119
+ sglang/srt/models/torch_native_llama.py,sha256=d8gVNurlVVZ-tD3Uc_aHyGCVUUp1gR8awOH4fLRZHDE,19145
120
+ sglang/srt/models/xverse.py,sha256=meyCCdrZRYNK70hnmydgwhHa1FTBhKekEdpG0_IGTWY,13564
121
+ sglang/srt/models/xverse_moe.py,sha256=xlrhJBAlRzxhp5o0WQU_2V5Uvf8I9fwZLOZBh95o3to,15673
122
+ sglang/srt/models/yivl.py,sha256=xcWqkuZ29FmBBJY6aKetwItWIPl-kfXK-QmgdLONles,4765
123
+ sglang/srt/openai_api/adapter.py,sha256=nZOVjZ-q4eULl19oT97_u7z63SQiWW7IzbYzJeWE7os,53069
124
+ sglang/srt/openai_api/protocol.py,sha256=EZ6G209rBEDP7cepO2kAYqE8wMe1ksYdN7to1iT97Lw,10248
125
+ sglang/srt/sampling/sampling_batch_info.py,sha256=qrijXoMhF-V_x3g6lumsfXgsGaPiKLIJ2pUz6ii-O2s,7735
126
+ sglang/srt/sampling/sampling_params.py,sha256=u1UWt9biIFXKymAg56RbkMa8oe5jxsoMvsv3cH7_kZ0,5692
127
+ sglang/srt/sampling/penaltylib/__init__.py,sha256=5vQw0Y5DSzmsoFg1IdMIKLwFVhYZ5ArADHVBYbSmOec,513
128
+ sglang/srt/sampling/penaltylib/orchestrator.py,sha256=kizcPnxtRawmDt6utRuhbk4yfNs5H5mx1DAlDVEZRv8,11328
129
+ sglang/srt/sampling/penaltylib/penalizers/frequency_penalty.py,sha256=IvYioX53Vq_ji-0Zhcz_r5mUa3T3GaIydVS6K4FhWfE,2557
130
+ sglang/srt/sampling/penaltylib/penalizers/min_new_tokens.py,sha256=MmfqRqJ-leSoY9iO5Hg_ILlX-M0M0tObYrxrb_quStg,3717
131
+ sglang/srt/sampling/penaltylib/penalizers/presence_penalty.py,sha256=0PlANTrR959foTA3Nj5qBE7ndaOZgG-9X6LhzlmEUc8,2533
132
+ sglang/srt/sampling/penaltylib/penalizers/repetition_penalty.py,sha256=v9jOgA0-I31WcrhIydiFbpy2ZJPLytFLGM98NRPd2sU,2820
133
+ sglang/test/few_shot_gsm8k.py,sha256=ll-gNbcv829IwSPXAZt4JIEIu8IR3APCLcX3BHOFVp8,3968
134
+ sglang/test/few_shot_gsm8k_engine.py,sha256=QQbrwOX6-cJDD3RZC_e7zPnt6aSo8JdF8X_lRHSjdDM,3886
135
+ sglang/test/run_eval.py,sha256=9yO0hXZOcn4abEOs96T-XPguDEklK16Ltco0pGF3zCg,4020
136
+ sglang/test/runners.py,sha256=JxfsGEW9L3cz87fHYmWqb3Vnbk6K1csLLLftR3LogxU,14297
137
+ sglang/test/simple_eval_common.py,sha256=r0G-9QLycs2ax3RMc44T_61fzMxlpTzv6pececC7lyY,12379
138
+ sglang/test/simple_eval_gpqa.py,sha256=8Xt9Bw05c7SZTYrCZgB68OZUqUbLo69ywiyx0bTvSUk,3220
139
+ sglang/test/simple_eval_humaneval.py,sha256=7lTi841NT58smNOtRwCedrdX9IWWypdLkOtaQOBy-GI,5687
140
+ sglang/test/simple_eval_math.py,sha256=6kGKNwNbLN-Af3Wj8WTimWhH-Xp3enDmSvvSjsgWUpk,2550
141
+ sglang/test/simple_eval_mgsm.py,sha256=wfbqJW9Rkc66vzq2fEMF6jchmoA8mw1OUiGU55cZ2B0,10261
142
+ sglang/test/simple_eval_mmlu.py,sha256=FkwamjGMjueTixymkedF-YiPloSLiy4ftILFUrKZ9XI,4357
143
+ sglang/test/test_activation.py,sha256=jkdNRzJnbd5OgZliQaIXpxovlcky17UrweomcOcMxoE,1442
144
+ sglang/test/test_layernorm.py,sha256=IacByD5d-stXjzBz8Ypamc7povlcedpKPbb_4JLgo3c,3720
145
+ sglang/test/test_programs.py,sha256=1Z0umrsUu9pagzyGH5SrXl_qhKSyTfUv_kWC2mcn0qo,18208
146
+ sglang/test/test_utils.py,sha256=zspkM9VSm6QXI4wVG-75r8ttGgylnPOEH7nuYjp5plU,22799
147
+ sglang/test/srt/sampling/penaltylib/utils.py,sha256=q98pQDikkmvvvvAG-AXMYaYte1iHHW2TFhKGtAeGvdE,12802
148
+ sglang-0.3.5.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
149
+ sglang-0.3.5.dist-info/METADATA,sha256=FQ8MBpLt6W0-43VhtuwEWgqomXaFwUumiBd6T8xPWG0,21099
150
+ sglang-0.3.5.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
151
+ sglang-0.3.5.dist-info/top_level.txt,sha256=yxhh3pYQkcnA7v3Bg889C2jZhvtJdEincysO7PEB09M,7
152
+ sglang-0.3.5.dist-info/RECORD,,
@@ -1,5 +1,5 @@
1
1
  Wheel-Version: 1.0
2
- Generator: setuptools (75.2.0)
2
+ Generator: setuptools (75.3.0)
3
3
  Root-Is-Purelib: true
4
4
  Tag: py3-none-any
5
5