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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Release-tagged ROCm 10 images for vllm/vllm-openai-rocm
- [Bug]: DelegatingParser.parse ignores model_output_token_ids, so markers written as plain text become tool calls or end reasoning (non-streaming)
- [BugFix] Parse FunctionGemma arguments the way the chat template writes them
- [BugFix] Reject logprobs larger than the vocabulary
- [Bugfix] Fix thinking_token_budget for Mistral control tokens
- Feat/cri mxfp4 moe
- [Feat][BI][1/N] add batch-invariant DeepSeek V4 support (top-k order)
- [Bugfix][Quantization] Keep fp32 weight_scale during batch-invariant FP8 dequantization
- [Bugfix][Benchmark] Keep oversampled request IDs unique after filtering
- Fix MFU/MBU dropping attention and FFN for renamed quantization methods (Fixes #58742)
- Docs
- Python not yet supported