sglang 0.3.4.post2__tar.gz → 0.3.5__tar.gz

sglang-0.3.5/PKG-INFO

@@ -0,0 +1,344 @@
+Metadata-Version: 2.1
+Name: sglang
+Version: 0.3.5
+Summary: SGLang is yet another fast serving framework for large language models and vision language models.
+License:                                  Apache License
+                                   Version 2.0, January 2004
+                                http://www.apache.org/licenses/
+        
+           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+        
+           1. Definitions.
+        
+              "License" shall mean the terms and conditions for use, reproduction,
+              and distribution as defined by Sections 1 through 9 of this document.
+        
+              "Licensor" shall mean the copyright owner or entity authorized by
+              the copyright owner that is granting the License.
+        
+              "Legal Entity" shall mean the union of the acting entity and all
+              other entities that control, are controlled by, or are under common
+              control with that entity. For the purposes of this definition,
+              "control" means (i) the power, direct or indirect, to cause the
+              direction or management of such entity, whether by contract or
+              otherwise, or (ii) ownership of fifty percent (50%) or more of the
+              outstanding shares, or (iii) beneficial ownership of such entity.
+        
+              "You" (or "Your") shall mean an individual or Legal Entity
+              exercising permissions granted by this License.
+        
+              "Source" form shall mean the preferred form for making modifications,
+              including but not limited to software source code, documentation
+              source, and configuration files.
+        
+              "Object" form shall mean any form resulting from mechanical
+              transformation or translation of a Source form, including but
+              not limited to compiled object code, generated documentation,
+              and conversions to other media types.
+        
+              "Work" shall mean the work of authorship, whether in Source or
+              Object form, made available under the License, as indicated by a
+              copyright notice that is included in or attached to the work
+              (an example is provided in the Appendix below).
+        
+              "Derivative Works" shall mean any work, whether in Source or Object
+              form, that is based on (or derived from) the Work and for which the
+              editorial revisions, annotations, elaborations, or other modifications
+              represent, as a whole, an original work of authorship. For the purposes
+              of this License, Derivative Works shall not include works that remain
+              separable from, or merely link (or bind by name) to the interfaces of,
+              the Work and Derivative Works thereof.
+        
+              "Contribution" shall mean any work of authorship, including
+              the original version of the Work and any modifications or additions
+              to that Work or Derivative Works thereof, that is intentionally
+              submitted to Licensor for inclusion in the Work by the copyright owner
+              or by an individual or Legal Entity authorized to submit on behalf of
+              the copyright owner. For the purposes of this definition, "submitted"
+              means any form of electronic, verbal, or written communication sent
+              to the Licensor or its representatives, including but not limited to
+              communication on electronic mailing lists, source code control systems,
+              and issue tracking systems that are managed by, or on behalf of, the
+              Licensor for the purpose of discussing and improving the Work, but
+              excluding communication that is conspicuously marked or otherwise
+              designated in writing by the copyright owner as "Not a Contribution."
+        
+              "Contributor" shall mean Licensor and any individual or Legal Entity
+              on behalf of whom a Contribution has been received by Licensor and
+              subsequently incorporated within the Work.
+        
+           2. Grant of Copyright License. Subject to the terms and conditions of
+              this License, each Contributor hereby grants to You a perpetual,
+              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+              copyright license to reproduce, prepare Derivative Works of,
+              publicly display, publicly perform, sublicense, and distribute the
+              Work and such Derivative Works in Source or Object form.
+        
+           3. Grant of Patent License. Subject to the terms and conditions of
+              this License, each Contributor hereby grants to You a perpetual,
+              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+              (except as stated in this section) patent license to make, have made,
+              use, offer to sell, sell, import, and otherwise transfer the Work,
+              where such license applies only to those patent claims licensable
+              by such Contributor that are necessarily infringed by their
+              Contribution(s) alone or by combination of their Contribution(s)
+              with the Work to which such Contribution(s) was submitted. If You
+              institute patent litigation against any entity (including a
+              cross-claim or counterclaim in a lawsuit) alleging that the Work
+              or a Contribution incorporated within the Work constitutes direct
+              or contributory patent infringement, then any patent licenses
+              granted to You under this License for that Work shall terminate
+              as of the date such litigation is filed.
+        
+           4. Redistribution. You may reproduce and distribute copies of the
+              Work or Derivative Works thereof in any medium, with or without
+              modifications, and in Source or Object form, provided that You
+              meet the following conditions:
+        
+              (a) You must give any other recipients of the Work or
+                  Derivative Works a copy of this License; and
+        
+              (b) You must cause any modified files to carry prominent notices
+                  stating that You changed the files; and
+        
+              (c) You must retain, in the Source form of any Derivative Works
+                  that You distribute, all copyright, patent, trademark, and
+                  attribution notices from the Source form of the Work,
+                  excluding those notices that do not pertain to any part of
+                  the Derivative Works; and
+        
+              (d) If the Work includes a "NOTICE" text file as part of its
+                  distribution, then any Derivative Works that You distribute must
+                  include a readable copy of the attribution notices contained
+                  within such NOTICE file, excluding those notices that do not
+                  pertain to any part of the Derivative Works, in at least one
+                  of the following places: within a NOTICE text file distributed
+                  as part of the Derivative Works; within the Source form or
+                  documentation, if provided along with the Derivative Works; or,
+                  within a display generated by the Derivative Works, if and
+                  wherever such third-party notices normally appear. The contents
+                  of the NOTICE file are for informational purposes only and
+                  do not modify the License. You may add Your own attribution
+                  notices within Derivative Works that You distribute, alongside
+                  or as an addendum to the NOTICE text from the Work, provided
+                  that such additional attribution notices cannot be construed
+                  as modifying the License.
+        
+              You may add Your own copyright statement to Your modifications and
+              may provide additional or different license terms and conditions
+              for use, reproduction, or distribution of Your modifications, or
+              for any such Derivative Works as a whole, provided Your use,
+              reproduction, and distribution of the Work otherwise complies with
+              the conditions stated in this License.
+        
+           5. Submission of Contributions. Unless You explicitly state otherwise,
+              any Contribution intentionally submitted for inclusion in the Work
+              by You to the Licensor shall be under the terms and conditions of
+              this License, without any additional terms or conditions.
+              Notwithstanding the above, nothing herein shall supersede or modify
+              the terms of any separate license agreement you may have executed
+              with Licensor regarding such Contributions.
+        
+           6. Trademarks. This License does not grant permission to use the trade
+              names, trademarks, service marks, or product names of the Licensor,
+              except as required for reasonable and customary use in describing the
+              origin of the Work and reproducing the content of the NOTICE file.
+        
+           7. Disclaimer of Warranty. Unless required by applicable law or
+              agreed to in writing, Licensor provides the Work (and each
+              Contributor provides its Contributions) on an "AS IS" BASIS,
+              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+              implied, including, without limitation, any warranties or conditions
+              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+              PARTICULAR PURPOSE. You are solely responsible for determining the
+              appropriateness of using or redistributing the Work and assume any
+              risks associated with Your exercise of permissions under this License.
+        
+           8. Limitation of Liability. In no event and under no legal theory,
+              whether in tort (including negligence), contract, or otherwise,
+              unless required by applicable law (such as deliberate and grossly
+              negligent acts) or agreed to in writing, shall any Contributor be
+              liable to You for damages, including any direct, indirect, special,
+              incidental, or consequential damages of any character arising as a
+              result of this License or out of the use or inability to use the
+              Work (including but not limited to damages for loss of goodwill,
+              work stoppage, computer failure or malfunction, or any and all
+              other commercial damages or losses), even if such Contributor
+              has been advised of the possibility of such damages.
+        
+           9. Accepting Warranty or Additional Liability. While redistributing
+              the Work or Derivative Works thereof, You may choose to offer,
+              and charge a fee for, acceptance of support, warranty, indemnity,
+              or other liability obligations and/or rights consistent with this
+              License. However, in accepting such obligations, You may act only
+              on Your own behalf and on Your sole responsibility, not on behalf
+              of any other Contributor, and only if You agree to indemnify,
+              defend, and hold each Contributor harmless for any liability
+              incurred by, or claims asserted against, such Contributor by reason
+              of your accepting any such warranty or additional liability.
+        
+           END OF TERMS AND CONDITIONS
+        
+           APPENDIX: How to apply the Apache License to your work.
+        
+              To apply the Apache License to your work, attach the following
+              boilerplate notice, with the fields enclosed by brackets "[]"
+              replaced with your own identifying information. (Don't include
+              the brackets!)  The text should be enclosed in the appropriate
+              comment syntax for the file format. We also recommend that a
+              file or class name and description of purpose be included on the
+              same "printed page" as the copyright notice for easier
+              identification within third-party archives.
+        
+           Copyright [yyyy] [name of copyright owner]
+        
+           Licensed under the Apache License, Version 2.0 (the "License");
+           you may not use this file except in compliance with the License.
+           You may obtain a copy of the License at
+        
+               http://www.apache.org/licenses/LICENSE-2.0
+        
+           Unless required by applicable law or agreed to in writing, software
+           distributed under the License is distributed on an "AS IS" BASIS,
+           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+           See the License for the specific language governing permissions and
+           limitations under the License.
+        
+Project-URL: Homepage, https://github.com/sgl-project/sglang
+Project-URL: Bug Tracker, https://github.com/sgl-project/sglang/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests
+Requires-Dist: tqdm
+Requires-Dist: numpy
+Requires-Dist: IPython
+Provides-Extra: runtime-common
+Requires-Dist: aiohttp; extra == "runtime-common"
+Requires-Dist: decord; extra == "runtime-common"
+Requires-Dist: fastapi; extra == "runtime-common"
+Requires-Dist: hf_transfer; extra == "runtime-common"
+Requires-Dist: huggingface_hub; extra == "runtime-common"
+Requires-Dist: interegular; extra == "runtime-common"
+Requires-Dist: orjson; extra == "runtime-common"
+Requires-Dist: packaging; extra == "runtime-common"
+Requires-Dist: pillow; extra == "runtime-common"
+Requires-Dist: psutil; extra == "runtime-common"
+Requires-Dist: pydantic; extra == "runtime-common"
+Requires-Dist: python-multipart; extra == "runtime-common"
+Requires-Dist: torchao; extra == "runtime-common"
+Requires-Dist: uvicorn; extra == "runtime-common"
+Requires-Dist: uvloop; extra == "runtime-common"
+Requires-Dist: zmq; extra == "runtime-common"
+Requires-Dist: outlines>=0.0.44; extra == "runtime-common"
+Requires-Dist: modelscope; extra == "runtime-common"
+Provides-Extra: srt
+Requires-Dist: sglang[runtime_common]; extra == "srt"
+Requires-Dist: torch; extra == "srt"
+Requires-Dist: vllm==0.6.3.post1; extra == "srt"
+Provides-Extra: srt-hip
+Requires-Dist: sglang[runtime_common]; extra == "srt-hip"
+Requires-Dist: torch; extra == "srt-hip"
+Requires-Dist: vllm==0.6.3.dev13; extra == "srt-hip"
+Provides-Extra: srt-xpu
+Requires-Dist: sglang[runtime_common]; extra == "srt-xpu"
+Provides-Extra: openai
+Requires-Dist: openai>=1.0; extra == "openai"
+Requires-Dist: tiktoken; extra == "openai"
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.20.0; extra == "anthropic"
+Provides-Extra: litellm
+Requires-Dist: litellm>=1.0.0; extra == "litellm"
+Provides-Extra: test
+Requires-Dist: jsonlines; extra == "test"
+Requires-Dist: matplotlib; extra == "test"
+Requires-Dist: pandas; extra == "test"
+Requires-Dist: sentence_transformers; extra == "test"
+Requires-Dist: accelerate; extra == "test"
+Requires-Dist: peft; extra == "test"
+Provides-Extra: all
+Requires-Dist: sglang[srt]; extra == "all"
+Requires-Dist: sglang[openai]; extra == "all"
+Requires-Dist: sglang[anthropic]; extra == "all"
+Requires-Dist: sglang[litellm]; extra == "all"
+Provides-Extra: all-hip
+Requires-Dist: sglang[srt_hip]; extra == "all-hip"
+Requires-Dist: sglang[openai]; extra == "all-hip"
+Requires-Dist: sglang[anthropic]; extra == "all-hip"
+Requires-Dist: sglang[litellm]; extra == "all-hip"
+Provides-Extra: all-xpu
+Requires-Dist: sglang[srt_xpu]; extra == "all-xpu"
+Requires-Dist: sglang[openai]; extra == "all-xpu"
+Requires-Dist: sglang[anthropic]; extra == "all-xpu"
+Requires-Dist: sglang[litellm]; extra == "all-xpu"
+Provides-Extra: dev
+Requires-Dist: sglang[all]; extra == "dev"
+Requires-Dist: sglang[test]; extra == "dev"
+Provides-Extra: dev-hip
+Requires-Dist: sglang[all_hip]; extra == "dev-hip"
+Requires-Dist: sglang[test]; extra == "dev-hip"
+Provides-Extra: dev-xpu
+Requires-Dist: sglang[all_xpu]; extra == "dev-xpu"
+Requires-Dist: sglang[test]; extra == "dev-xpu"
+
+<div align="center"  id="sglangtop">
+<img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400" margin="10px"></img>
+
+[![PyPI](https://img.shields.io/pypi/v/sglang)](https://pypi.org/project/sglang)
+![PyPI - Downloads](https://img.shields.io/pypi/dm/sglang)
+[![license](https://img.shields.io/github/license/sgl-project/sglang.svg)](https://github.com/sgl-project/sglang/tree/main/LICENSE)
+[![issue resolution](https://img.shields.io/github/issues-closed-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)
+[![open issues](https://img.shields.io/github/issues-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)
+
+</div>
+
+--------------------------------------------------------------------------------
+
+| [**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) |
+[**Join Bi-Weekly Development Meeting**](https://docs.google.com/document/d/1xEow4eIM152xNcRxqZz9VEcOiTQo8-CEuuQ5qTmkt-E/edit?usp=sharing) |
+
+## News
+- [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)).
+- [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/)).
+- [2024/07] Faster Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM) ([blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/)).
+
+<details>
+<summary>More</summary>
+
+- [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
+- [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/)).
+- [2024/01] SGLang provides up to **5x faster inference** with RadixAttention ([blog](https://lmsys.org/blog/2024-01-17-sglang/)).
+- [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)).
+
+</details>
+
+## About
+SGLang is a fast serving framework for large language models and vision language models.
+It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language.
+The core features include:
+
+- **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).
+- **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.
+- **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.
+- **Active Community**: SGLang is open-source and backed by an active community with industry adoption.
+
+## Install
+See [https://sgl-project.github.io/start/install.html](https://sgl-project.github.io/start/install.html)
+
+## Backend: SGLang Runtime (SRT)
+See [https://sgl-project.github.io/backend/backend.html](https://sgl-project.github.io/backend/backend.html)
+
+## Frontend: Structured Generation Language (SGLang)
+See [https://sgl-project.github.io/frontend/frontend.html](https://sgl-project.github.io/frontend/frontend.html)
+
+## Benchmark And Performance
+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/)
+
+## Roadmap
+[Development Roadmap (2024 Q4)](https://github.com/sgl-project/sglang/issues/1487)
+
+## Citation And Acknowledgment
+Please cite our paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.
+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).

sglang-0.3.5/README.md

@@ -0,0 +1,59 @@
+<div align="center"  id="sglangtop">
+<img src="https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png" alt="logo" width="400" margin="10px"></img>
+
+[![PyPI](https://img.shields.io/pypi/v/sglang)](https://pypi.org/project/sglang)
+![PyPI - Downloads](https://img.shields.io/pypi/dm/sglang)
+[![license](https://img.shields.io/github/license/sgl-project/sglang.svg)](https://github.com/sgl-project/sglang/tree/main/LICENSE)
+[![issue resolution](https://img.shields.io/github/issues-closed-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)
+[![open issues](https://img.shields.io/github/issues-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)
+
+</div>
+
+--------------------------------------------------------------------------------
+
+| [**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) |
+[**Join Bi-Weekly Development Meeting**](https://docs.google.com/document/d/1xEow4eIM152xNcRxqZz9VEcOiTQo8-CEuuQ5qTmkt-E/edit?usp=sharing) |
+
+## News
+- [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)).
+- [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/)).
+- [2024/07] Faster Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM) ([blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/)).
+
+<details>
+<summary>More</summary>
+
+- [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
+- [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/)).
+- [2024/01] SGLang provides up to **5x faster inference** with RadixAttention ([blog](https://lmsys.org/blog/2024-01-17-sglang/)).
+- [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)).
+
+</details>
+
+## About
+SGLang is a fast serving framework for large language models and vision language models.
+It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language.
+The core features include:
+
+- **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).
+- **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.
+- **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.
+- **Active Community**: SGLang is open-source and backed by an active community with industry adoption.
+
+## Install
+See [https://sgl-project.github.io/start/install.html](https://sgl-project.github.io/start/install.html)
+
+## Backend: SGLang Runtime (SRT)
+See [https://sgl-project.github.io/backend/backend.html](https://sgl-project.github.io/backend/backend.html)
+
+## Frontend: Structured Generation Language (SGLang)
+See [https://sgl-project.github.io/frontend/frontend.html](https://sgl-project.github.io/frontend/frontend.html)
+
+## Benchmark And Performance
+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/)
+
+## Roadmap
+[Development Roadmap (2024 Q4)](https://github.com/sgl-project/sglang/issues/1487)
+
+## Citation And Acknowledgment
+Please cite our paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.
+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).

{sglang-0.3.4.post2 → sglang-0.3.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sglang"
-version = "0.3.4.post2"
+version = "0.3.5"
 description = "SGLang is yet another fast serving framework for large language models and vision language models."
 readme = "README.md"
 requires-python = ">=3.8"
@@ -13,16 +13,19 @@ classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: Apache Software License",
 ]
-dependencies = ["requests", "tqdm", "numpy"]
+dependencies = ["requests", "tqdm", "numpy", "IPython"]
 
 [project.optional-dependencies]
 runtime_common = ["aiohttp", "decord", "fastapi", "hf_transfer", "huggingface_hub", "interegular",
     "orjson", "packaging", "pillow", "psutil", "pydantic", "python-multipart",
     "torchao", "uvicorn", "uvloop", "zmq",
     "outlines>=0.0.44", "modelscope"]
+srt = ["sglang[runtime_common]", "torch", "vllm==0.6.3.post1"]
+# HIP (Heterogeneous-computing Interface for Portability) for AMD
+# => base docker rocm/vllm-dev:20241022, not from public vllm whl
+srt_hip = ["sglang[runtime_common]", "torch", "vllm==0.6.3.dev13"]
 # xpu is not enabled in public vllm and torch whl,
 # need to follow https://docs.vllm.ai/en/latest/getting_started/xpu-installation.htmlinstall vllm
-srt = ["sglang[runtime_common]", "torch", "vllm==0.6.3.post1"]
 srt_xpu = ["sglang[runtime_common]"]
 
 openai = ["openai>=1.0", "tiktoken"]
@@ -37,8 +40,10 @@ test = [
     "peft",
 ]
 all = ["sglang[srt]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]"]
+all_hip = ["sglang[srt_hip]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]"]
 all_xpu = ["sglang[srt_xpu]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]"]
 dev = ["sglang[all]", "sglang[test]"]
+dev_hip = ["sglang[all_hip]", "sglang[test]"]
 dev_xpu = ["sglang[all_xpu]", "sglang[test]"]
 
 [project.urls]

{sglang-0.3.4.post2 → sglang-0.3.5}/sglang/api.py

@@ -99,7 +99,7 @@ def gen(
     regex: Optional[str] = None,
     json_schema: Optional[str] = None,
 ):
-    """Call the model to generate. See the meaning of the arguments in docs/en/sampling_params.md"""
+    """Call the model to generate. See the meaning of the arguments in docs/sampling_params.md"""
 
     if choices:
         return SglSelect(

{sglang-0.3.4.post2 → sglang-0.3.5}/sglang/bench_latency.py

@@ -129,9 +129,9 @@ def load_model(server_args, port_args, tp_rank):
 
     model_config = ModelConfig(
         server_args.model_path,
-        server_args.trust_remote_code,
+        trust_remote_code=server_args.trust_remote_code,
         context_length=server_args.context_length,
-        model_override_args=json.loads(server_args.json_model_override_args),
+        model_override_args=server_args.json_model_override_args,
     )
     model_runner = ModelRunner(
         model_config=model_config,
@@ -550,4 +550,4 @@ if __name__ == "__main__":
     except Exception as e:
         raise e
     finally:
-        kill_child_process(os.getpid(), including_parent=False)
+        kill_child_process()

{sglang-0.3.4.post2 → sglang-0.3.5}/sglang/bench_server_latency.py

@@ -15,7 +15,6 @@ import dataclasses
 import itertools
 import json
 import multiprocessing
-import os
 import time
 from typing import Tuple
 
@@ -70,7 +69,7 @@ def launch_server_internal(server_args):
     except Exception as e:
         raise e
     finally:
-        kill_child_process(os.getpid(), including_parent=False)
+        kill_child_process()
 
 
 def launch_server_process(server_args: ServerArgs):
@@ -176,7 +175,7 @@ def run_benchmark(server_args: ServerArgs, bench_args: BenchArgs):
             )
     finally:
         if proc:
-            kill_child_process(proc.pid)
+            kill_child_process(proc.pid, include_self=True)
 
     print(f"\nResults are saved to {bench_args.result_filename}")
 

{sglang-0.3.4.post2 → sglang-0.3.5}/sglang/bench_serving.py

@@ -222,6 +222,85 @@ async def async_request_openai_completions(
     return output
 
 
+async def async_request_truss(
+    request_func_input: RequestFuncInput,
+    pbar: Optional[tqdm] = None,
+) -> RequestFuncOutput:
+    api_url = request_func_input.api_url
+
+    prompt = request_func_input.prompt
+
+    async with aiohttp.ClientSession(timeout=AIOHTTP_TIMEOUT) as session:
+        payload = {
+            "model": request_func_input.model,
+            "prompt": prompt,
+            "temperature": 0.0,
+            "best_of": 1,
+            "max_tokens": request_func_input.output_len,
+            "stream": not args.disable_stream,
+            "ignore_eos": not args.disable_ignore_eos,
+            **request_func_input.extra_request_body,
+        }
+        headers = {"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"}
+
+        output = RequestFuncOutput()
+        output.prompt_len = request_func_input.prompt_len
+
+        generated_text = ""
+        ttft = 0.0
+        st = time.perf_counter()
+        most_recent_timestamp = st
+        try:
+            async with session.post(
+                url=api_url, json=payload, headers=headers
+            ) as response:
+                if response.status == 200:
+                    async for chunk_bytes in response.content:
+                        chunk_bytes = chunk_bytes.strip()
+                        if not chunk_bytes:
+                            continue
+
+                        chunk = remove_prefix(chunk_bytes.decode("utf-8"), "data: ")
+                        latency = time.perf_counter() - st
+                        if chunk == "[DONE]":
+                            pass
+                        else:
+                            data = json.loads(chunk)
+
+                            # NOTE: Some completion API might have a last
+                            # usage summary response without a token so we
+                            # want to check a token was generated
+                            if data["choices"][0]["delta"]["content"]:
+                                timestamp = time.perf_counter()
+                                # First token
+                                if ttft == 0.0:
+                                    ttft = time.perf_counter() - st
+                                    output.ttft = ttft
+
+                                # Decoding phase
+                                else:
+                                    output.itl.append(timestamp - most_recent_timestamp)
+
+                                most_recent_timestamp = timestamp
+                                generated_text += data["choices"][0]["delta"]["content"]
+
+                    output.generated_text = generated_text
+                    output.success = True
+                    output.latency = latency
+                    output.output_len = request_func_input.output_len
+                else:
+                    output.error = response.reason or ""
+                    output.success = False
+        except Exception:
+            output.success = False
+            exc_info = sys.exc_info()
+            output.error = "".join(traceback.format_exception(*exc_info))
+
+    if pbar:
+        pbar.update(1)
+    return output
+
+
 async def async_request_sglang_generate(
     request_func_input: RequestFuncInput,
     pbar: Optional[tqdm] = None,
@@ -350,6 +429,7 @@ ASYNC_REQUEST_FUNCS = {
     "lmdeploy": async_request_openai_completions,
     "trt": async_request_trt_llm,
     "gserver": async_request_gserver,
+    "truss": async_request_truss,
 }
 
 
@@ -873,6 +953,7 @@ def run_benchmark(args_: argparse.Namespace):
             "vllm": 8000,
             "trt": 8000,
             "gserver": 9988,
+            "truss": 8080,
         }.get(args.backend, 30000)
 
     model_url = (
@@ -905,9 +986,20 @@ def run_benchmark(args_: argparse.Namespace):
     elif args.backend == "gserver":
         api_url = args.base_url if args.base_url else f"{args.host}:{args.port}"
         args.model = args.model or "default"
+    elif args.backend == "truss":
+        api_url = (
+            f"{args.base_url}/v1/models/model:predict"
+            if args.base_url
+            else f"http://{args.host}:{args.port}/v1/models/model:predict"
+        )
 
     # Get model name
     if args.model is None:
+        if args.backend == "truss":
+            print(
+                "Please provide a model with `--model` when using truss backend. e.g. --model meta-llama/Llama-3.1-8B-Instruct"
+            )
+            sys.exit(1)
         try:
             response = requests.get(model_url)
             model_list = response.json().get("data", [])

{sglang-0.3.4.post2 → sglang-0.3.5}/sglang/global_config.py

@@ -14,9 +14,15 @@ class GlobalConfig:
         self.default_backend = None
 
         # Runtime constants: New generation token ratio estimation
-        self.init_new_token_ratio = 0.7
-        self.base_min_new_token_ratio = 0.1
-        self.new_token_ratio_decay = 0.001
+        self.default_init_new_token_ratio = float(
+            os.environ.get("SGLANG_INIT_NEW_TOKEN_RATIO", 0.7)
+        )
+        self.default_min_new_token_ratio_factor = float(
+            os.environ.get("SGLANG_MIN_NEW_TOKEN_RATIO_FACTOR", 0.14)
+        )
+        self.default_new_token_ratio_decay_steps = float(
+            os.environ.get("SGLANG_NEW_TOKEN_RATIO_DECAY_STEPS", 600)
+        )
 
         # Runtime constants: others
         self.retract_decode_steps = 20