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
- [Doc] Sleep mode: what stays on the GPU
- [Feature] Add an EvenMoE backend: Moe load balancer: pluggable expert placement and replica routing
- [Bugfix] google/gemma4-31B-it --kv-cache-dtype fp8 --kv-cache-dtype-skip-layers sliding_window crashed
- [Bugfix][Frontend] Restore request ID response header replacement
- [LoRA] Avoid redundant classification head computation
- [Bug]: B200 cross-node TP=4 startup hangs without MNNVL during communicator initialization
- [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
- Python not yet supported