Skip to content
GPULlama3 Build & Run

[FP16] Improved performance by fusing dequantize with compute in kernels: 20-30% Inference Speedup #176

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 #176

Run time

Learn about OS pricing on GitHub Actions
Job Run time
code-quality
12s
build-and-run (ptx)
3m 20s
build-and-run (opencl)
3m 33s
7m 5s