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
- [ROCm][DP] QuickReduce combine for allgather/reducescatter MoE
- [Feature]: KV-pool-saturated admission retries inflate decode TPOT ~2.3x: request automatic admission backoff
- [ROCm][Qwen4Exp][DeepSeek-V4.1] Add per_token PLE/Engram lookup mode
- [Bugfix][EPLB] Start the async rearrangement interval after the last layer commits
- [BugFix] Reject logprobs larger than the vocabulary
- [Bugfix] Fix thinking_token_budget for Mistral control tokens
- [Bugfix][Quantization] Keep fp32 weight_scale during batch-invariant FP8 dequantization
- [Bugfix][ROCm] Avoid unused index caches in MiniMax-M3 sharing layers
- [Bugfix][MoE] Preserve invalid expert IDs in DeepEP LL round-robin mapping
- [Quantization][MoE] Prefer Humming over Marlin for MXFP8 MoE on SM12x
- Docs
- Python not yet supported