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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Quantization][Autoround][ARK] Add ARK W4A16(moe) Support
- Add MoNe experts pruning support
- [RFC]: Lookahead-aware prefix-cache hashing for EAGLE-style draft models
- [ROCm][Perf] Use AITER tuned GEMM for the MoE router gate
- [Bugfix][Frontend] message-level tool declarations
- [Hybrid KV Cache] Retain finalized Mamba decode checkpoints for prefix caching
- Added SVE128 and SVE256 support to vectorizer backend.
- [ROCm] Unify ViT FlashAttention backend selection
- [Bugfix][Gemma4] Keep image bidirectional attention within the sliding window on the V2 model runner
- [Bugfix] Validate tensor dtypes and topk_weights length in the moe_wna16 GEMM op wrappers
- Docs
- Python not yet supported