LLM inference in C/C++
C++ ggml
ci : add HF_TOKEN to self-hosted workflows (#25706)
Georgi Gerganovc81029373dd7
diff --git a/.github/workflows/build-self-hosted.yml b/.github/workflows/build-self-hosted.ymlindex 1a71ed8277..441a897e50 100644--- a/.github/workflows/build-self-hosted.yml+++ b/.github/workflows/build-self-hosted.yml@@ -6,7 +6,7 @@ on:branches:- masterpaths: [- '.github/workflows/build.yml',+ '.github/workflows/build-self-hosted.yml','**/CMakeLists.txt','**/.cmake','**/*.h',@@ -48,6 +48,8 @@ concurrency:cancel-in-progress: trueenv:+ # note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)+ HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}GGML_NLOOP: 3GGML_N_THREADS: 1LLAMA_ARG_LOG_COLORS: 1diff --git a/.github/workflows/server-self-hosted.yml b/.github/workflows/server-self-hosted.ymlindex 2dcd6d7425..d8266d7ee5 100644--- a/.github/workflows/server-self-hosted.yml+++ b/.github/workflows/server-self-hosted.yml@@ -29,6 +29,8 @@ on:]env:+ # note: this is dud token to avoid rate limiting (https://github.com/ggml-org/llama.cpp/pull/25706#issuecomment-4979941302)+ HF_TOKEN: ${{ secrets.HF_TOKEN_CI }}LLAMA_ARG_LOG_COLORS: 1LLAMA_ARG_LOG_PREFIX: 1LLAMA_ARG_LOG_TIMESTAMPS: 1