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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] Add SM>=89 guard for Triton block FP8 kernel
- Revert "[Quantization] Consolidate experts_int8 with fp8 online quantization" (#38463)
- [Feature] TurboQuant: support hybrid models and uniform quantization
- [CPU][RISC-V] Add RVV-optimized attention kernels for RISC-V Vector Extension
- [Bugfix] moe lora align kernel grid
- [vLLM IR] Port activations (gelu) to IR op
- Feature/intern s1 parser
- [Feature] Add Triton kernel JIT compilation monitor for inference
- [Bugfix][LMCache MP Connector] Fix fallback adapter cache_salt signature mismatch
- [WIP]Ray async scheduling with pp
- Docs
- Python not yet supported