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
- [ROCm][Perf] Speed up large MoE ReLU-squared on gfx90a
- [Bugfix][MoE] Use backend expert count for workspace sizing
- [XPU] WA topk_sigmoid argument mismatch for XPU platform
- [Bug]: GLM-5.2-NVFP4 produces garbled/incorrect output and hits NotImplementedError in forward_mha on GB10 (SM121a) with FLASHINFER_MLA_SPARSE_SM120
- [Kernel] ReplaySSM: cache SSM inputs for faster Gated DeltaNet speculative decode
- [ROCm] Support AITER paged attention on gfx90a
- [Bugfix] Route DSv4 sparse-indexer prefill top-k around NaN-broken kernel path on SM12x
- [Bugfix] Reject whitespace-only bad_words in SamplingParams
- [Bugfix] Handle non-text frames in realtime speech WebSocket
- [Bug]: Prefill with prompt length == 1 + num_speculative_tokens misclassified as uniform decode → FULL spec-verify cudagraph skips GDN/hybrid recurrent-state write → deterministic garbage (any spec method incl. ngram; v0.25.1 & v0.26.0)
- Docs
- Python not yet supported