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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][V1] triton_unified_attention: apply tile_mask in USE_TD KV load
- Add SM120 NVFP4 KV cache support
- docs: add AI Badgr hosted GPU deployment option
- [Model Runner V2][Spec Decode]Support peagle spec decode
- [Bug]: Setting prompt_embeds does not work for vision-language models
- [Bug]: [Bug] CUDA illegal memory access with Gemma-4-31B-it + RedHatAI/gemma-4-31B-it-speculator.dflash (DFlash)
- feat: add optional torchembed RoPE backend
- Fix cumem allocator cleanup on allocation failures
- [Bug]: Negative CUDA graph memory estimation (-35 GiB) with MTP speculative decoding leads to severe KV cache over-allocation and OOM
- [Bugfix] Harden allowed_token_ids metadata for spec-decode
- Docs
- Python not yet supported