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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Spec Decode][MRV2] Add prefill_context_kv_only for P/D prefill instances
- [Attention] Sync FA with upstream (54b044c8)
- [Model] Nemotron-H: serve FP8 linears as W8A16 with bf16_activations
- [Bugfix][Kernel] Check pointer alignment before vectorizing activation kernels
- [Perf][DSv4.1] Skip Q computation in replay KV prewrite
- [Feature]: Update tilelang to 0.1.15
- [Multimodal] Faster multimodal input path under concurrent image traffic (parallel preprocessing + sizable shm tensor arena)
- [Bugfix] Tolerate NVML device query failures in startup diagnostics
- [ROCm][Bugfix] Keep AITER MLA split metadata alive for CUDA graph replay
- [Security] Restrict EC NIXL reads to configured producer peers
- Docs
- Python not yet supported