You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Marlin24 kernel code has landed and the actual quantization code, official implementation, and paper is about to drop with another ~30% increase on top of Marlin. Looks like the official release is going to be very soon to coincide with the publication of the Marlin24 research paper from iDAS
Marlin24 kernel code has landed and the actual quantization code, official implementation, and paper is about to drop with another ~30% increase on top of Marlin. Looks like the official release is going to be very soon to coincide with the publication of the Marlin24 research paper from iDAS
vllm-project/vllm#4790
The text was updated successfully, but these errors were encountered: