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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][DI][CI] Swap container ionic RoCE userspace to a host-compatible AINIC channel
- [Feature]: Cap default build parallelism by available memory in setup.py
- Raise OpenAI LM-eval server startup budget
- [RFC] CLI configuration without runtime initialization
- [Security] Strip uppercase hex addresses from client error messages
- [Core] Preempt hybrid requests whose sync KV load failed
- [Perf] Select batched Marlin tile from token load
- [Bugfix] Make DSA prefill top-k deterministic on equal scores
- [Perf][Distributed] Make MNNVL Lamport RS/AG message-size caps configurable
- [Bug]: Humming MoE permute scratch memory scales with number of MoE layers
- Docs
- Python not yet supported