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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: MiMo V2.5-Pro Bad Outputs with specdec and async scheduling
- [Feature]: Add cache_salt support for Anthropic Messages API
- [Bug]: Qwen3.5 CPU backend crashes in mamba_utils.batch_memcpy when Triton is unavailable
- [Bugfix] Add CPU fallback for mamba batch memcpy
- [RFC]: Support for Domino speculative decoding in vLLM
- [Bug]: When the startup parameter "--max-model-len auto --enable-chunked-prefill -- enable-prefix-caching --max-num-batched-tokens 65536", garbled characters are displayed in the output of the GLM-5.1-NVFP4 model deployed using the VLLM Docker image.
- [Bug]: sparse-MLA indexer error with GLM 5.2 NVFP4 on RTX 6000 Pro SM120
- [Kernel][MoE] Integrate TokenSpeed Mxfp4 MOE Kernel
- [Bug]: Qwen3.5 397B NVFP4 Crashes on B300
- [Kernel] Support batch invariance for WNA16 Marlin MoE
- Docs
- Python not yet supported