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
- [V1][Core] Autotune encoder cache budget
- [Bugfix] Fix start_idx for computing slot mapping to avoid uninitiali…
- [Usage]: Running guided decoding on vllm for TPUs
- [Spec Decode] Add Script for converting HF Eagle checkpoint to vLLM compatible checkpoint
- add model_glm code
- [Installation]: Could not find a version that satisfies the requirement xgrammar>=0.1.6; platform_machine == "x86_64" (from vllm) (from versions: none)
- [Bugfix] support to run partially 2:4 model with CompressedTensors24 scheme
- [Bugfix] Multi-sequence broken
- [New Model]: Jinja template for Llama3.3
- [Bug]: Engine is gracefully shutting down
- Docs
- Python not yet supported