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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [KVConnector] Let MultiConnector compose sub-connector hits
- [Hybrid KV Cache][Kimi K3] SSM decode checkpoints for prefix caching
- [Bugfix][XPU] Fix Mamba state pointer overflow
- [Kernel] Fuse SiTU activation + FP8 quant in persistent MoE kernel
- [Kimi-K3][ROCm] Fuse KDA upper-triangle zeroing
- [MoE][OOT] Add prepare/finalize factory registry
- [NIXL] Feed decoder the prefiller's first sampled token in toy proxy
- [Bugfix][KV Connector][Mooncake] Avoid stale recv completion after early abort
- [ROCm][Performance] Eliminate per-decode allocations and output copy …
- [Bugfix] Handle single-shard FP8 Marlin MoE padding
- Docs
- Python not yet supported