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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Drop incomplete tool-call markup in non-streaming to match streaming
- [Bugfix][MLA] Use guarded dtype for kv_c_normed cast in _compute_prefill_context
- [Bugfix] Require quack-kernels>=0.4.1 for cutlass-dsl 4.5+ compatibility
- [ROCm] Add VLLM_ROCM_ENABLE_CUDAGRAPH forcibly enable cudagraph for encoder-decoder models
- [Kernel] ReplaySSM: cache SSM inputs instead of state for faster standard and speculative decode (Mamba2 + GDN)
- [Bugfix] Fall back to V1 model runner when UVA is unavailable (WSL2)
- [Perf] Keep H2D transfers dense in fused-MoE weight loading
- [Perf][Frontend] Add opt-in incremental prompt-encoding cache for multi-turn chat
- [Spec Decode][Perf] Rowwise-fp8 draft lm_head for DSpark (opt-in)
- [ModelRunner V2] Support custom logits processors
- Docs
- Python not yet supported