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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [V1] Fix CPU sampler ignoring request seeds in mixed batches (#51226)
- [Bug]: gemma4 parser keeps literal quote characters when the model writes array/object string values in plain JSON or Python syntax instead of <|"|>
- [Bug]: VLLM_BATCH_INVARIANT=1 not deterministic under tensor parallelism (TP>1); fuse_allreduce_rms fused all-reduce is the cause
- [ROCm][Perf] Skip redundant sparse index remap on non-indexer layers
- [K3 Perf] Flash kda out kernel for prefill, 1.1~1.4x kernel performance improvement
- [ROCm][Perf] Fuse the DSA indexer prologue with AITER
- [1/N] HiSparse: host-resident sparse-MLA decode hot-buffering
- [3/N] Share HiSparse host cache across TP ranks
- [RFC][Spec Decode] Trust checkpoint-declared method over path-name heuristics
- [Bugfix] Keep top-level quantization_config when benchmark_moe descends via --model-prefix
- Docs
- Python not yet supported