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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI] Remove lm-eval configs that no config list references
- [CI] Remove the unused run-benchmarks harness and genai-perf test deps
- [CI][ROCm] Drop MI300 MRv2 groups and other dead pipeline leftovers
- [CI] Remove A100 steps that the pipeline generator no longer emits
- [CI] Remove never-run tool_use extended configs and the unused BFCL script
- [Usage]: Recommended way to serve multiple models (e.g. embedding) on a single GPU
- [ROCm][Perf][GLM-5.3-Flash] Shard the kpool indexer prefill rows across TP on ROCm
- [Hybrid KV Cache] [2/N] Support finalized decode checkpoints with hidden-state drafting
- [ROCm][Perf][GLM-5.3-Flash] Enable AITER fused shared experts on gfx942
- [ROCm][Perf] Gather MLA DCP query with AITER all-gather
- Docs
- Python not yet supported