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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- fix: reject non-text content in system/developer messages
- Adding support to Sarvam's MoE models
- Elastic AFD
- [Frontend] Add --disable-log-prefix flag and VLLM_DISABLE_LOG_PREFIX env var
- [Bugfix][Frontend] Fix IndexError in Mistral tool parser during streaming tool calls
- [Bugfix] Fix CUDA compatibility path setting for both datacenter and consumer NVIDIA GPUs
- [Spec-Decode] Add DynamicProposer for per-sequence dynamic speculative decoding
- [Feature]: Improve sparse embedding pooling output format for better efficiency and usability
- [W8A8 Block Linear Refactor][4/N] Make all scaled MM kernels inherit from common generic base.
- [Feature]: Community Help Wanted: Migrate Remaining Linear Methods into Kernel Abstraction
- Docs
- Python not yet supported