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
- [Bug]: 'int' object has no attribute 'expansion'
- [Core] Support sparse KV cache framework
- [Installation]: Failed to install the packages at entrypoint
- [RFC]: Support sparse KV cache framework
- [core][distributed] add message queue for cross-node broadcast
- [Usage]: Is this an error ? "async_llm_engine.py:154] Aborted request cmpl-xxxxx"
- [Bugfix] Add a more helpful load model OOM message
- [Usage]: qwen2-1.5b-gptq-in4 single gpu multiprocessing deployment fail
- [Misc]: how to understand: NUM_ELEMS_PER_THREAD = HEAD_SIZE / THREAD_GROUP_SIZE
- api_server.py: error: unrecognized arguments: --tool-use-prompt-template --enable-api-tools --enable-auto-tool-choice
- Docs
- Python not yet supported