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
- Support Voxtral audio generation in the Transformers backend
- fix(responses): reject code_interpreter tool call missing "code" field
- kernels: fused silu_and_mul + dynamic per-token FP8 quantization
- [Bug] DeepSeek-V4 on SM12x: NaN MQA logits drive top_k_per_row_prefill to emit uninitialized smem as indices -> illegal memory access
- [Bug]: [Regression] Assertion res == CUresult::CUDA_SUCCESS failed in FlashMLA (phase1.cuh) for DeepSeek-V4 on v0.26.0 (Works in v0.25.0)
- [ROCm][Perf] Speed up single-group MoE routing
- [Model] Enable batch-invariant mixed decode and prefill for Qwen GDN
- [Model Loader] Introduce custom weight copy
- [Feature]: per gpu gpu-memory-utilization
- [Bug][KV Offload] `HIT_PENDING` has no deadline; a stalled write can defer requests until the client timeout
- Docs
- Python not yet supported