Single-source cross-platform GPU LLM inference with Slang and Rust
UD2.120 (Chavanne) | Day 1 | 13:05 - 13:25 | Speakers: Crozet Sébastien
Single-source cross-platform GPU LLM inference with Slang and Rust
Abstract
Leveraging Rust and Khronos' emerging Slang initiative, we introduce our efforts toward a cross-platform GPU LLM inference ecosystem. With a single-source approach we aim to minimize backend-specific code and foster community participation by writing inference kernels once and run them everywhere.
Links
External Links
Notice: The placeholder video image is licensed under CC BY-SA 4.0. The original image can be found hereChanges made to the image are: Cropped the image to a new ratio, part of the image was cut off.
