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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Lwilkinson/kv layout/kv content pack
- KV events: BlockStored token_ids can span skipped Mamba align blocks while block_hashes omit them
- [Kernel][MoE] Delegate finalize output-buffer allocation to prepare_finalize
- [Experiment][Model Runner V2][Spec Decode] sharded rejection sampling
- [2/N][KV-Cache Layout Refactor] Pack K/V into the content dim across attention backends
- [3/N][KV-Cache Layout Refactor] Standardize Mamba cache; drop `get_transfer_cache_regions`
- up FI fp8 moe topk to 32
- Vram semaphore infra
- [XPU] Enable v1/sample tests on XPU CI
- [Bug]: [0.22.0] When using Hidden State Extraction, if enable-prefix-caching is turned on, the length of hidden_states obtained will be inconsistent with the length of token_ids.
- Docs
- Python not yet supported