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
- [Feature] Add Responses Session Store for cross-request incremental token reuse
- [Bugfix][MoE] Fall back quantization-only backends to auto for unquantized layers
- [Perf][DSv4.1] Reuse physical top-k selection across decode layers
- [Bugfix][KV Connector] Preserve PyTorch family during Docker dependency install
- [Frontend] Add Responses API compaction endpoint
- [Bug]: MooncakeStoreConnector drops decode-phase Mamba states for hybrid Mamba/GDN models
- [Bug] GLM-5.3-Flash with TP=1 per rank (DP4) fails at CUDA-graph capture in fused_recurrent_kda: grid.z = batch x 64 heads exceeds 65535
- [Performance] GLM-5.3-Flash on 4x GB200 TP4: p99 ITL 15-20x SGLang's at c>=32; prefill-containing steps run outside CUDA graphs; raising --max-cudagraph-capture-size to the chunk size cuts the tail by about half (data)
- [CI] Select Arm tests for runner changes
- [Kernel][Perf] Pad large unaligned SM100 block FP8 linear inputs
- Docs
- Python not yet supported