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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] step3 tool parser: record streamed arguments so the finalizer does not duplicate them
- [Bugfix][Spec Decode] Reject ngram_gpu with pipeline parallelism
- fix(security): harden media URL fetching against SSRF
- [Bugfix] Use 64-bit token offsets in fused GDN post-conv prep
- [ROCm][Model][MiniMax-M3] Context-parallel sparse lightning indexer (Triton, opt-in)
- [Bug]: RowWiseTorchFP8ScaledMMLinearKernel is selected on RDNA4 (gfx1201) from v0.28 and costs 5-24% decode
- [ROCm][Model][MiniMax-M3] Context-parallel AITER sparse indexer (fp8, opt-in)
- [ROCm] Calibrate gfx950 decode Top-K routing by rows × compressed-context
- [Profiler] Add per-session profiling controls to Python and Rust frontends
- [Bug]: fp8 FlashMLA sparse decode crashes at engine init with --enforce-eager on SM90 (dummy-run aten::new_empty dispatch failure, size-dependent)
- Docs
- Python not yet supported