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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix: cap ngram gpu drafts by max model length
- tracing: propagate active server span via headers
- [Perf][DSv4/DSv3.2] Add cluster-cooperative topK kernel for low-latency scenarios
- [Core][Ray] Fix get_node_ip and driver_ip on multi-NIC nodes
- [Quantization] add hadamard transform + online quantization support to humming
- Revert "[Perf] Re-enable flashinfer autotune by default and cleanup" (#42857)
- [Perf] Optimize DeepSeek V4 fused qkv RMSNorm
- platform: replace current_platform.is_tpu() with device_name check at hardware-gating sites
- [POC][Observability][Frontend] Add observability for pooling entrypoints.
- [Feature] Triton kernel dispatcher
- Docs
- Python not yet supported