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
- [Bug]: enable_prefix_caching=True but zero hits for any shared prefix shorter than one attention block on hybrid checkpoints (2096 / 1920 tokens), with nothing in the logs or metrics naming the minimum
- [Attention][Quantization] Support FP8-K / NVFP4-V KV cache
- [Build] Restore generic wheel for no_device targets
- [Bug]: PD-disaggregation cannot use PCIe P2P for KV transfer on Intel Arc Pro B60 (BMG)
- [Bugfix] Seed align-mode Mamba state_idx in Mamba blocks
- [ROCm] fix MI455 customed paged attn
- [Bugfix] Close the socket test_loopback_bind creates when bind fails
- [Performance]: [MRV2][PP]: Post sampled-result receives closer to T+PP consumption
- [ROCm][Perf] Add opt-in prequantized FP8 attention for the Qwen3.8 model family
- [KV Connector][Mooncake] Send disaggregated KV as whole pages when la…
- Docs
- Python not yet supported