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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Add assertion for scale_attn_weights in GPT-2
- refactor: unify duplicated flashinfer utility modules
- [Perf] Optimize `sampled_token_ids` using numpy and remove `tolist`, 0.9% E2E throughput improvement
- [Bug]: Server hangs indefinitely during inference with Qwen3.5-27B-FP8 (vLLM nightly)
- [Bug]: Assertionerror when using OffloadingConnector: assert len(req.block_hashes) >= num_gpu_blocks
- [Bug]: Qwen3.5 NVFP4 models crash on ARM64 GB10 DGX Spark (CUDA illegal instruction during generation)
- [Model Runner V2] support qwen35 / mamba hybrid model
- [Bugfix] Fix empty channel/recipient in harmony for /v1/responses
- feat: batch-aware expert pruning (XShare) for MoE models
- Yejin/bench ramp fix v2
- Docs
- Python not yet supported