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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Raise ImportError early when xxhash is unavailable for prefix caching
- Fix FlashMLA test API
- [Bugfix] Fail fast on custom AR graph buffer count mismatch
- [Feature] Add support for timed trace replay in `vllm bench serve` to replay Moonshot and Alibaba workload traces
- Revert "[MoE Refactor] Remove MoE DP chunking" (#39107)
- [v1] Allow attention backends to declare custom KV cache page size
- [CI] Reorganize release pipeline: separate nightly vs release sections
- [MyPy] Fix mypy for `vllm/benchmarks`
- Update gpu.xpu.inc.md to use triton-xpu 3.7.0
- [Kernel] Optimize moeTopK memory access with shared memory and fix indexing bugs
- Docs
- Python not yet supported