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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: option to return hidden states
- [Usage] [Bug]: run inference on mistralai/Mixtral-8x7B-Instruct-v0.1 with tensor parallel > 1 (currently not working)
- [Bug]: The first token generated after prefill occupies the GPU memory but virtual block
- [Feature]: Load new LoRA adapters on request
- [Bug]: AssertionError in neuron_model_runner.py assert len(block_table) == 1
- [Core] Log more GPU memory reservation info
- [Bug]: Special tokens split when decoding after 0.4.0.post1
- [Bug]: I used vllm=0.4.1 to run the squeezellm, I meet the bug RuntimeError: t == DeviceType::CUDA INTERNAL ASSERT FAILED at "/opt/hostedtoolcache/Python/3.10.14/x64/lib/python3.10/site-packages/torch/include/c10/cuda/impl/CUDAGuardImpl.h":25, please report a bug to PyTorch.
- [Usage]: prefix-caching
- [Bug]: i cant't use vllm lora with 2gpus, but 1 gpu is ok
- Docs
- Python not yet supported