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
- [Bug]: Gemma 4: Unsloth LoRA adapters are ignored during inference despite successful loading
- Fix hipErrorCapturedEvent on RoCM when using LoRA with cuda graphs
- [Bug]: ngram speculative decoding changes greedy output on Qwen3-0.6B / A100
- [Quantization] Remove duplication in select_mxfp4_moe_backend
- fix: support MIG UUIDs in CUDA_VISIBLE_DEVICES
- [BUGFIX] Parse or convert thinking chunks given content format
- [Kernel] Enable in-place SSM state access for GDN chunk prefill kernel (Qwen3.5, Qwen3 Next, OLMo-Hybrid)
- [LoRA][Perf] Overlap LoRA weight H2D copies with compute via side CUDA stream
- [Perf] Replace cudaMemsetAsync with in-kernel cleanup for persistent_topk
- fix(spec-decode): resync thinking state before target logits in rejec…
- Docs
- Python not yet supported