vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: [Batch-Invariant-Kernels] GDN_ATTN does not support batch-invariant mode for Qwen3.5/Qwen3.6 GDN models
- [Bugfix] Reject incompatible user-specified --block-size before model load
- [RFC]: Session-centric KV-cache orchestration over typed session identity
- [Bug]: Gemma 4 MTP speculative decoding crashes during CUDA graph capture (`_suppress_token_ids` is a Python list, not a device tensor)
- feat(mxfp4): add MXFP4 expert cache support to DeepSeek V4
- [RFC]: manylinux compatibility baseline for aarch64 binary dependencies
- [Kernel] MXFP4 indexer cache for GLM-5.2 / DSA (glm_moe_dsa)
- fix(security): validate INT4 W4A8 MoE inputs to prevent OOB read and …
- 还不支持[Usage]: vllm 0.25版本在tp=8并行的时候走dflash 和dspark 命中 attention后端的时候出现错误报错定位 CUDA error (/workspace/.deps/vllm-flash-attn-src/hopper/flash_api.cpp:697): invalid configuration argument 8个worker(TP0-TP7)
- feat: Add LongCat-Next multimodal MoE model support
- Docs
- Python not yet supported