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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: DeepSeekV4 DSpark CUDA graph capture failure on H100
- [Bugfix] [Build] Fix DeepGEMM SM90 paged mqa `prefix_sum` out of range
- [AMD][K3] Write KDA decode output straight into the layer buffer
- [RFC]: Adopt otel genai semantic conventions for metrics
- [Bug]: VLLM_BATCH_INVARIANT=1 returns non-identical logprobs across repeats of a byte-identical concurrent workload at ~44 co-resident sequences
- [Bug]: compressed-tensors models with format: dense sparsity_config fail to load
- [Dependency]: Bump torchvision to a release containing the CVE-2026-65918 fix
- [ROCm][MLA] Dispatch gfx942 verify to Gluon
- [Performance]: Qwen3.6-35B-A3B (Qwen3_5MoeForConditionalGeneration) BF16 GDN backbone isn't quantized — ~80% of per-step reads, caps decode
- [Perf] Add an adaptive prefill delayer for data-parallel serving
- Docs
- Python not yet supported