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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] Add HIP paged attention kernel for TurboQuant k8v4 decode
- [Hardware][Power]Add Power VSX Attention Backend and fix l2 Cache Crash
- [Bugfix][Rocm]Aiter MoE re-uses existing tensor addresses after weight update.
- [ROCM] [FEAT] Integrate Aiter hipBLASLt GEMM online tuning
- [bugfix] Fix floating-point comparisons in GPU sampling kernels to use epsilon…
- [Bugfix] Clarify FLASHINFER limitation for per-attention-head KV quantization
- [RFC] Rust-accelerated control plane (scheduler + KV cache manager) — PoC
- Feat/tq rocm decode v2
- [Bug]: v0.19.1 Crash with CUDA invalid argument / Segfault when using KV Offloading + EAGLE3 + Expert Parallel (on 8x H20 141GB)
- refactor: make is_neox_style configurable for glm
- Docs
- Python not yet supported