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 Request: QuIP# 2-bit Quantization Support
- Support tiktoken as an option for tokenizer
- Allow single LLM step to generate multiple tokens
- Add Tail-Free sampling
- [Feature Request] Tree speculate
- Add support for long-context beacon models: KeyError: 'model.beacon_embed_tokens.weight'
- [WIP] Implement fused_moe kernel with cutlass grouped gemm
- Add docker-compose.yml and corresponding .env
- vllm keeps hanging when using djl-deepspeed
- Add tokenizer_init_kwargs into vllm engine
- Docs
- Python not yet supported