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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core] Add remaining copy counts to KV removal events
- [Bugfix] Fall back to native sampling when FlashInfer cannot target the GPU
- fix: NVFP4 quantization out_dtype should match model dtype, not torch default
- [Bugfix][Reload] Preserve unmanaged tensor addresses across weight reload
- [CT] Support Humming for WNA16 MoE
- [Bugfix] Fix Marlin W4A8 signed scale corruption
- [Bugfix] Fail fast in MPClient ready-wait when an engine core proc dies during startup
- [Doc] Fix stale code references to moved and removed files
- [PARSER][Mistral] unified engine-based parser for reasoning and tool calls
- [XPU] Fix the accuracy issue for DeepSeekV4 on DP scenarios
- Docs
- Python not yet supported