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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [BugFix][Spec Decode] Log EAGLE draft RoPE and warn when config omits rope keys
- [BugFix] Combine return_sampling_mask SamplingParams precondition errors
- [BugFix][Quantization] Surface FP8 kernel rejection reasons for fp8_per_channel
- [Doc]: Advisory GHSA-mm38-5g96-7j6x lists affected versions as <= 0.8.5, but the code it names ships in 0.10.2 to 0.24.x
- [Perf][Frontend] Add bounded segment tokenizer cache to HF renderers
- [Kernel][Spec Decode] Fuse temperature scaling into the rejection-sampling kernels
- [Bugfix][Spec Decode] Fix DFlash capture on FLEX_ATTENTION and honor drafter enforce_eager
- [Bug]: An explicit truncation_side drops the special tokens the tokenizer adds
- [Bugfix] Require hybrid KV cache manager for hybrid models
- [Bug]: LLM.__repr__ raises AttributeError when the worker model is not a torch module
- Docs
- Python not yet supported