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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Draft][Experimental][CUDA][VLM] Scaffold AttentionPack-style KV compression path
- [Kernel] Implement CUDA kernel for ReLUSquaredActivation (relu^2)
- [Bugfix][MoE] Fix hardcoded SharedExperts output buffer size for DBO ubatches
- Support FP8 block-quant TP when intermediate size per rank is not divisible by block_n
- Revert "[Perf] Change Trtllm fp8 MoE to use Shuffled Weights and BlockMajorK Layout" (#38993)
- [Feature] KV cache per-token-head Int2/Int4 Quantization + Triton_Quant_KV Interface
- Fix Qwen3 reasoning tool calls embedded inside think
- [Bug]: Sync EPLB rearrangement hangs indefinitely with DP8 + EP on B200
- [Bug]: runai_safetensors_weights_iterator yields tensors in nondeterministic order, breaking FP8 inference on some platforms
- [BugFix][Parser] Fixing Qwen3.5 tool call parsing
- Docs
- Python not yet supported