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 supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Quant] Add SupportsQuant and packed_modules_mapping to all models
- [Core] Add a level 3 sleep/wake_up that offloads tensors to disk
- [Doc]: Does vllm CPU backend support Intel AMX?
- Ray named test
- [INTEL-HPU] Deepseek R1 model enabling for Intel Gaudi
- [Usage]: LLM.beam_search is much slower in vLLM 0.7.3 compared to 0.5.4
- [Bug]: API Connection Error after concurrent API calls
- [Kernel] Update cutlass FP8 blockwise to use upstream CUTLASS
- [Usage]: Logprobs Scaling with O(n) Complexity – Unexpected Performance Degradation
- [Feature]: `reasoning_tokens` in Chat Completion Response `usage`
- Docs
- Python not yet supported