Skip to content
Build and Test

[llama32_1b] full-int4 ELF2 for decode (-48% latency, -68% weight mem… #6497

Sign in to view logs

[llama32_1b] full-int4 ELF2 for decode (-48% latency, -68% weight mem…

[llama32_1b] full-int4 ELF2 for decode (-48% latency, -68% weight mem… #6497

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Build and Test with ROCm runtime (Assert, 22.04)
11m 54s
Build and Test with ROCm runtime (Release, 22.04)
12m 50s
24m 44s