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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] Enable DeepSelect sparse indexer top-k on sm90
- [Bugfix] Implement fail-fast blocking during the startup phase
- [Feature]: Helm chart: add an optional ServiceMonitor with a configurable regex filter to reduce the number of exported metrics
- [Bugfix][Mistral] Map arbitrary tool call IDs instead of truncating
- [Docs] Update speech-to-text preprocessing guide
- [Benchmarks] Fix inverted language filter in multi-turn ShareGPT conv…
- [Transformers backend] Support Mamba2 (SSD) layers
- [Bugfix] Don't unmap cuMem allocations freed while asleep
- [Bug]: AOT compilation cache does not track quantization kernel selection — same-version kernel switch loads stale artifact and crashes
- [Bugfix][Compile] Include resolved quantization kernel selection in AOT compile cache key
- Docs
- Python not yet supported