From 4d0a7cbc617e384fc355077a304c883b5c7d4fb6 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Mon, 22 Sep 2025 08:31:40 +0300 Subject: [PATCH] ci : adjust params for less runtime (#16167) * ci : adjust params for less runtime * ci : gate BF16 on some hardware * ci : move extra tests to Arm runner --- .github/workflows/build.yml | 2 +- ci/run.sh | 72 +++++++++++++++++++++---------------- tools/main/main.cpp | 2 +- 3 files changed, 44 insertions(+), 32 deletions(-) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 510b25b759..a7efce0071 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -1300,7 +1300,7 @@ jobs: - name: Test id: ggml-ci run: | - bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp + GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp ggml-ci-x64-nvidia-v100-cuda: runs-on: [self-hosted, Linux, X64, NVIDIA, V100] diff --git a/ci/run.sh b/ci/run.sh index 64bc88b335..09417ef619 100755 --- a/ci/run.sh +++ b/ci/run.sh @@ -259,7 +259,7 @@ function gg_sum_test_scripts_release { } function gg_get_model { - local gguf_0="$MNT/models/qwen3/0.6B/ggml-model-bf16.gguf" + local gguf_0="$MNT/models/qwen3/0.6B/ggml-model-f16.gguf" if [[ -s $gguf_0 ]]; then echo -n "$gguf_0" else @@ -345,8 +345,10 @@ function gg_run_qwen3_0_6b { (time cmake -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log (time make -j$(nproc) ) 2>&1 | tee -a $OUT/${ci}-make.log + python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf --outtype f16 python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_models}/ggml-model-bf16.gguf --outtype bf16 + model_f16="${path_models}/ggml-model-f16.gguf" model_bf16="${path_models}/ggml-model-bf16.gguf" model_q8_0="${path_models}/ggml-model-q8_0.gguf" model_q4_0="${path_models}/ggml-model-q4_0.gguf" @@ -372,36 +374,40 @@ function gg_run_qwen3_0_6b { ./bin/llama-quantize ${model_bf16} ${model_q5_k} q5_k ./bin/llama-quantize ${model_bf16} ${model_q6_k} q6_k - (time ./bin/llama-cli -no-cnv --model ${model_bf16} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-bf16.log - (time ./bin/llama-cli -no-cnv --model ${model_q8_0} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log - (time ./bin/llama-cli -no-cnv --model ${model_q4_0} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_0.log - (time ./bin/llama-cli -no-cnv --model ${model_q4_1} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_1.log - (time ./bin/llama-cli -no-cnv --model ${model_q5_0} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_0.log - (time ./bin/llama-cli -no-cnv --model ${model_q5_1} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_1.log - (time ./bin/llama-cli -no-cnv --model ${model_q2_k} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q2_k.log - (time ./bin/llama-cli -no-cnv --model ${model_q3_k} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q3_k.log - (time ./bin/llama-cli -no-cnv --model ${model_q4_k} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_k.log - (time ./bin/llama-cli -no-cnv --model ${model_q5_k} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_k.log - (time ./bin/llama-cli -no-cnv --model ${model_q6_k} -t 1 -ngl 99 -c 2048 -s 1234 -n 256 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q6_k.log + (time ./bin/llama-cli -no-cnv --model ${model_f16} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-f16.log + (time ./bin/llama-cli -no-cnv --model ${model_bf16} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-bf16.log + (time ./bin/llama-cli -no-cnv --model ${model_q8_0} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log + (time ./bin/llama-cli -no-cnv --model ${model_q4_0} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_0.log + (time ./bin/llama-cli -no-cnv --model ${model_q4_1} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_1.log + (time ./bin/llama-cli -no-cnv --model ${model_q5_0} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_0.log + (time ./bin/llama-cli -no-cnv --model ${model_q5_1} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_1.log + (time ./bin/llama-cli -no-cnv --model ${model_q2_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q2_k.log + (time ./bin/llama-cli -no-cnv --model ${model_q3_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q3_k.log + (time ./bin/llama-cli -no-cnv --model ${model_q4_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_k.log + (time ./bin/llama-cli -no-cnv --model ${model_q5_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_k.log + (time ./bin/llama-cli -no-cnv --model ${model_q6_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q6_k.log - (time ./bin/llama-perplexity --model ${model_bf16} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-bf16.log - (time ./bin/llama-perplexity --model ${model_q8_0} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log - (time ./bin/llama-perplexity --model ${model_q4_0} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_0.log - (time ./bin/llama-perplexity --model ${model_q4_1} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_1.log - (time ./bin/llama-perplexity --model ${model_q5_0} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_0.log - (time ./bin/llama-perplexity --model ${model_q5_1} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_1.log - (time ./bin/llama-perplexity --model ${model_q2_k} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q2_k.log - (time ./bin/llama-perplexity --model ${model_q3_k} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q3_k.log - (time ./bin/llama-perplexity --model ${model_q4_k} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_k.log - (time ./bin/llama-perplexity --model ${model_q5_k} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_k.log - (time ./bin/llama-perplexity --model ${model_q6_k} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-tg-q6_k.log + (time ./bin/llama-perplexity --model ${model_f16} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-f16.log + if [ -z ${GG_BUILD_NO_BF16} ]; then + (time ./bin/llama-perplexity --model ${model_bf16} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-bf16.log + fi + (time ./bin/llama-perplexity --model ${model_q8_0} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log + (time ./bin/llama-perplexity --model ${model_q4_0} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_0.log + (time ./bin/llama-perplexity --model ${model_q4_1} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_1.log + (time ./bin/llama-perplexity --model ${model_q5_0} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_0.log + (time ./bin/llama-perplexity --model ${model_q5_1} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_1.log + (time ./bin/llama-perplexity --model ${model_q2_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q2_k.log + (time ./bin/llama-perplexity --model ${model_q3_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q3_k.log + (time ./bin/llama-perplexity --model ${model_q4_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_k.log + (time ./bin/llama-perplexity --model ${model_q5_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_k.log + (time ./bin/llama-perplexity --model ${model_q6_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q6_k.log - (time ./bin/llama-imatrix --model ${model_bf16} -f ${wiki_test} -t 1 -ngl 99 -c 2048 -b 512 --chunks 4 ) 2>&1 | tee -a $OUT/${ci}-imatrix.log + (time ./bin/llama-imatrix --model ${model_f16} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-imatrix.log - (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 2048 -fa off ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log - (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 2048 -fa on ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log - (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 2048 -fa off ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log - (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 2048 -fa on ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log + (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 1024 -fa off ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log + (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 10 -c 1024 -fa on ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log + (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 1024 -fa off ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log + (time ./bin/llama-save-load-state --model ${model_q4_0} -ngl 99 -c 1024 -fa on ) 2>&1 | tee -a $OUT/${ci}-save-load-state.log function check_ppl { qnt="$1" @@ -416,7 +422,10 @@ function gg_run_qwen3_0_6b { return 0 } - check_ppl "bf16" "$(cat $OUT/${ci}-tg-bf16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + check_ppl "f16" "$(cat $OUT/${ci}-tg-f16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + if [ -z ${GG_BUILD_NO_BF16} ]; then + check_ppl "bf16" "$(cat $OUT/${ci}-tg-bf16.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log + fi check_ppl "q8_0" "$(cat $OUT/${ci}-tg-q8_0.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log check_ppl "q4_0" "$(cat $OUT/${ci}-tg-q4_0.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log check_ppl "q4_1" "$(cat $OUT/${ci}-tg-q4_1.log | grep "^\[1\]")" | tee -a $OUT/${ci}-ppl.log @@ -440,7 +449,10 @@ function gg_sum_qwen3_0_6b { gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)" gg_printf '- perplexity:\n%s\n' "$(cat $OUT/${ci}-ppl.log)" gg_printf '- imatrix:\n```\n%s\n```\n' "$(cat $OUT/${ci}-imatrix-sum.log)" - gg_printf '- bf16:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-bf16.log)" + gg_printf '- f16:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-f16.log)" + if [ -z ${GG_BUILD_NO_BF16} ]; then + gg_printf '- bf16:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-bf16.log)" + fi gg_printf '- q8_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q8_0.log)" gg_printf '- q4_0:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q4_0.log)" gg_printf '- q4_1:\n```\n%s\n```\n' "$(cat $OUT/${ci}-tg-q4_1.log)" diff --git a/tools/main/main.cpp b/tools/main/main.cpp index 865ea4a2f7..083fc0cf26 100644 --- a/tools/main/main.cpp +++ b/tools/main/main.cpp @@ -178,7 +178,7 @@ int main(int argc, char ** argv) { return 1; } - // Start the non-batch threadpool in the paused state + // start the non-batch threadpool in the paused state tpp.paused = true; }