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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Recurring CUDA kernel hang on 2x DGX Spark (GB10, sm_12.1) with MiniMax-M2.7-NVFP4, TP=2 across 2 nodes
- [Docs][ROCm] Add ROCm-specific troubleshooting section
- [Bug]: DeepseekV4Attention crashes with KeyError: scale_fmt on non-canonical DSv4 quantizations
- Bump fsspec from 2024.12.0 to 2026.4.0
- Bump pyrate-limiter from 3.7.0 to 4.2.0
- [Core] block_pool: sort the list of allocated free blocks
- [Perf] Prefetch torch_key and triton_key at worker startup
- [Spec Decode] Fix Gemma4 DFlash batched verification
- [Bug]: Latest Nightly build with TurboQuant KV cache crashes on large chunked continuation prefill after workspace lock ( testing PR #39931 implementing TQ on Hybrid Attention Models e.g Qwen3.5-9B)
- [vLLM IR] Nits
- Docs
- Python not yet supported