gitaskhub

The only deployed sparse FP4 GEMM on SM120: beats CUTLASS 80b on every shape, wins end-to-end request latency in 81 of 112 serving regimes vs dense NVFP4.

Stars · 3
Language · Python
License · MIT
Ask anything about this repo to start.

By chatting or signing in you agree to the Terms and chat-message logging (revocable in History).