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
- [Feature]: make the memory profiling assert configurable to enable parallel testing reusing gpus
- [Bug]: `cudaErrorLaunchFailure` in worker under concurrent native KV offloading with DeepSeek-V4-Flash (frequency depends on kv-cache dtype)
- Small note from HVTracker: would you be open to adding your trust badge?
- [Bug]: Out of bounds in moe_permute
- [Bug]: Out of bounds in moe_wna16.cu
- [Core][KV Connector] Avoid hybrid KV load failure crash
- fix: propagate revision pin to FunAudioChat and Tarsier2 artifact loads
- serving: MM warmup background overlap needs real serialization via _mm_executor (design review needed)
- (security) Enforce allowed_tools at execution time for Responses API
- Revert "[Render] Add `/derender` endpoints for disaggregated postprocessing" (#43606)
- Docs
- Python not yet supported