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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: support for prompt cache
- [Bug]: cannot run model when TP>1 (already run debug file)
- [Bug]: Gemma 27B Produces no Outputs (2B and 9B work fine)
- [Bug]: TPU single-host v5e-8 HBM OOM with Llama 3.1 70B and tpu_int8 quantization
- [Bug]: missing 'Finished request xxxx' log
- [Feature]: Allow max_tokens = 0
- [Installation]: Adding opentelemetry packages in container image
- [Bug]: vllm crashes when preemption of priority scheduling is triggered on vllm-0.6.3.dev173+g36ea7907.d20241011
- [Not for review] Test multimodal with adag
- [Bug]: Exception in worker VllmWorkerProcess while processing method init_device: NCCL error: unhandled cuda error
- Docs
- Python not yet supported