Skip to content
Back to pull request #10326

LLM: support quantized kv cache for Mistral in transformers >=4.36.0 #4244

Sign in to view logs

LLM: support quantized kv cache for Mistral in transformers >=4.36.0

LLM: support quantized kv cache for Mistral in transformers >=4.36.0 #4244

Run time

Learn about OS pricing on GitHub Actions
Job Run time
setup-python-version
1s
llm-cpp-build / check-linux-avx512-artifact
2s
llm-cpp-build / check-linux-amx-artifact
4s
llm-cpp-build / check-windows-avx2-artifact
4s
llm-cpp-build / check-linux-avxvnni-artifact
3s
llm-cpp-build / check-windows-avx-artifact
7s
llm-cpp-build / check-windows-avx-vnni-artifact
2s
llm-cpp-build / linux-build-avx512
2m 15s
llm-cpp-build / linux-build-avxvnni
2m 1s
llm-cpp-build / windows-build-avx-vnni
3m 16s
llm-cpp-build / windows-build-avx2
1m 2s
llm-cpp-build / linux-build-amx
59s
llm-cpp-build / windows-build-avx
45s
llm-unit-test-on-arc (2.1, 3.9)
15m 50s
llm-unit-test (windows, 3.9)
11m 8s
llm-unit-test-on-arc (2.0, 3.9)
12m 25s
llm-unit-test (ubuntu-20.04-lts, 3.9)
14m 16s
1h 4m 20s