Skip to content
GPULlama3 Build & Run

[FP16] Improved performance by fusing dequantize with compute in kernels: 20-30% Inference Speedup #148

Sign in to view logs

[FP16] Improved performance by fusing dequantize with compute in kernels: 20-30% Inference Speedup

[FP16] Improved performance by fusing dequantize with compute in kernels: 20-30% Inference Speedup #148

Run time

Learn about OS pricing on GitHub Actions
Job Run time
code-quality
25s
build-and-run (ptx)
7m 9s
build-and-run (opencl)
4m 21s
11m 55s