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 supported40 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Metrics] Report vllm:iteration_tokens_total for each chunked prefill
- [Feature]: Publish a standalone Rust frontend docker image
- [Bugfix] Handle nested dicts in RoPE _make_hashable for caching
- [Bugfix] Add missing dflash_config to DSpark speculators config
- [Bugfix] compressed-tensors: allow format=dense sparsity_config to load
- [Bugfix] compressed-tensors: allow format=dense sparsity_config to load (backport #51189 to v0.24.0)
- [Bugfix] compressed-tensors: allow format=dense sparsity_config to load (backport #51189 to v0.26.0)
- [Parity with CUDA vLLM]: ROCm Mooncake out of the box in prebuilt Docker
- fix: Skip empty DeepSeek-V4 FlashInfer attention slices
- [Bugfix][Sampler] Honor per-request seeds in partially-seeded CPU batches
- Docs
- Python not yet supported