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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Fix DFlash first prefill lookahead allocation
- [Bug]: Eagle 2/3 acceptance length regression over time
- qwen2.5-omni: offload multimodal features to CPU after GPU processing
- [Core][Model] Add GDN (Qwen3.5) support to NIXL P/D disaggregation
- [Bugfix] Surface KV cache load errors in OpenAI responses
- [Bugfix][Model] Remove 30s audio cap in Qwen3-ASR dummy inputs builder
- [Cache] Opt-in: stop caching KV blocks after thinking start tokens
- [Core] Prioritize preempted requests in v1 Scheduler Priority Queue
- warmup: skip deep_gemm warmup when DeepGEMM is not available
- [Bugfix] Fix circular import errors caused by lazy loading in vllm/__init__.py
- Docs
- Python not yet supported