LLM inference in C/C++
C++ ggml
tests : fix running server tests on windows (#26889)
Georgi Gerganov9afff1b7483d
diff --git a/.github/workflows/server.yml b/.github/workflows/server.ymlindex d5abf1d236..9fb4b4ba10 100644--- a/.github/workflows/server.yml+++ b/.github/workflows/server.yml@@ -167,15 +167,17 @@ jobs:- name: Testsid: server_integration_tests+ shell: bashrun: |cd tools/server/tests- $env:PYTHONIOENCODING = ":replace"+ export PYTHONIOENCODING=":replace"./tests.sh- name: Slow testsid: server_integration_tests_slowif: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}+ shell: bashrun: |cd tools/server/tests- $env:SLOW_TESTS = "1"+ export SLOW_TESTS="1"./tests.sh