Skip to content
PR Tests

[ROCm] Optimize kgemm_4bit_inference_naive for ROCm, use it for batch sizes other than 1 #255

Sign in to view logs

[ROCm] Optimize kgemm_4bit_inference_naive for ROCm, use it for batch sizes other than 1

[ROCm] Optimize kgemm_4bit_inference_naive for ROCm, use it for batch sizes other than 1 #255

Run time

Learn about OS pricing on GitHub Actions
Job Run time
CUDA (linux-x64, T4, 11.8.0) / build
3m 51s
CUDA (linux-x64, L40S, 13.0.2) / build
4m 6s
CUDA (linux-x64, T4, 12.8.1) / build
5m 26s
CUDA (linux-x64, T4, 13.0.2) / build
3m 50s
CUDA (windows, T4, 11.8.0, 2.7.1, https://download.pytorch.org/whl/cu118) / build
4m 5s
CUDA (linux-x64, A10, 13.0.2) / build
4m 32s
CUDA (linux-x64, A10, 11.8.0) / build
2m 41s
CUDA (linux-x64, L40S, 12.8.1) / build
3m 59s
CUDA (linux-x64, L40S, 11.8.0) / build
3m 26s
CUDA (linux-x64, A10, 12.8.1) / build
3m 36s
CPU (linux-aarch64, 2.11.0) / build
21s
CPU (macos, 2.3.1) / build
21s
CPU (linux-x64, 2.11.0) / build
13s
CPU (linux-x64, icelake, 2.3.1) / build
17s
CPU (macos, 2.11.0) / build
17s
CPU (linux-aarch64, 2.5.1) / build
14s
CPU (linux-x64, 2.3.1) / build
20s
CPU (linux-x64, icelake, 2.11.0) / build
13s
CPU (linux-x64, icelake, 2.11.0) / test
20m 45s
CPU (linux-x64, 2.11.0) / test
27m 48s
CPU (linux-aarch64, 2.5.1) / test
14m 53s
CPU (macos, 2.11.0) / test
23m 12s
CPU (linux-x64, icelake, 2.3.1) / test
19m 27s
CPU (linux-x64, 2.3.1) / test
22m 43s
CPU (macos, 2.3.1) / test
27m 17s
CPU (linux-aarch64, 2.11.0) / test
15m 28s
CUDA (linux-x64, A10, 11.8.0) / test
4m 15s
CUDA (linux-x64, L40S, 11.8.0) / test
3m 41s
CUDA (linux-x64, A10, 12.8.1) / test
7m 32s
CUDA (linux-x64, T4, 13.0.2) / test
9m 10s
CUDA (linux-x64, T4, 11.8.0) / test
5m 35s
CUDA (linux-x64, L40S, 12.8.1) / test
6m 24s
CUDA (linux-x64, L40S, 13.0.2) / test
6m 11s
CUDA (windows, T4, 11.8.0, 2.7.1, https://download.pytorch.org/whl/cu118) / test
1m 46s
CUDA (linux-x64, A10, 13.0.2) / test
7m 16s
CUDA (linux-x64, T4, 12.8.1) / test
9m 24s
4h 34m 35s
⚡