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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Revert "[QeRL] Compose online quantization with quantized reloading" (#38032)
- [Transformers v5] Vendor HCXVisionConfig for compatibility
- fix(metrics): capture num_preemptions before _reset() clears it in log()
- [Feature]: Better Flashinfer compilation logging
- [Refactor] Consolidate Tool type alias in tool_parsers/utils.py
- [Bugfix][Tool Parser] Fix Kimi-K2 argument truncation when decoding bundles `tool_call_end` and `tool_call_begin` into a single streaming delta
- [Core] Add soft thinking token budget with progressive logit bias
- [Model] Use AutoWeightsLoader for InternLM2
- [Model Loader] fix BGE-M3 compatibility
- [Feature]: Batch invariance on 3090
- Docs
- Python not yet supported