diff --git a/ci/run.sh b/ci/run.sh index 4d75c7f179..30a6bf3291 100755 --- a/ci/run.sh +++ b/ci/run.sh @@ -460,10 +460,10 @@ function gg_run_qwen3_0_6b { # https://github.com/ggml-org/llama.cpp/actions/runs/39639985732 if [ -z ${GG_BUILD_WEBGPU} ]; then (time ./bin/test-llama-context --model ${model_q4_0} -ngl 10 -c 1024 -fa off --no-op-offload) 2>&1 | tee -a $OUT/${ci}-test-llama-context.log - (time ./bin/test-llama-context --model ${model_q4_0} -ngl 10 -c 1024 -fa on --no-op-offload) 2>&1 | tee -a $OUT/${ci}-test-llama-context.log (time ./bin/test-llama-context --model ${model_q4_0} -ngl 99 -c 1024 -fa off ) 2>&1 | tee -a $OUT/${ci}-test-llama-context.log - (time ./bin/test-llama-context --model ${model_q4_0} -ngl 99 -c 1024 -fa on ) 2>&1 | tee -a $OUT/${ci}-test-llama-context.log fi + (time ./bin/test-llama-context --model ${model_q4_0} -ngl 10 -c 1024 -fa on --no-op-offload) 2>&1 | tee -a $OUT/${ci}-test-llama-context.log + (time ./bin/test-llama-context --model ${model_q4_0} -ngl 99 -c 1024 -fa on ) 2>&1 | tee -a $OUT/${ci}-test-llama-context.log check_ppl "f16" "$(cat $OUT/${ci}-tg-f16.log | grep "^\[1\]")" if [ -z ${GG_BUILD_NO_BF16} ]; then