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]: CPU offload cannot pin regions of 512 GiB or more (single cudaHostRegister call)
- [Bugfix][KV Offload] Register the offload region in chunks
- Pin AITER for 1250 build
- [Bugfix] Initialize per-token-head KV scale regions once per storage
- [Bugfix] Preserve user PYTORCH_CUDA_ALLOC_CONF keys in _scoped_allocator_max_split
- [Bugfix][Core] Include cgroup root CPU quota
- [Bug]: DeepSeek-V4-Flash-0731 crashes on RTX PRO 5000 because FlashInfer cannot reshape a tensor with 0 elements into the shape [0, -1]
- [Rust][Benchmark] Fix multi-turn input token accounting
- [Bugfix] Validate cached QuTLASS revision before reuse
- [Bugfix] Embed the full batch in the prompt_embeds path so LoRA metadata stays in range
- Docs
- Python not yet supported