patch: increasing MAX_REPETITION_THRESHOLD to allow complex agentic workflows
This commit is contained in:
@@ -22,7 +22,7 @@ RUN dnf -y --nodocs --setopt=install_weak_deps=False \
|
||||
rocm-llvm rocm-device-libs hip-runtime-amd hip-devel \
|
||||
rocblas rocblas-devel hipblas hipblas-devel rocm-cmake libomp-devel libomp \
|
||||
rocminfo radeontop \
|
||||
git-core vim sudo rsync \
|
||||
git-core vim sudo rsync patch \
|
||||
&& dnf clean all && rm -rf /var/cache/dnf/*
|
||||
|
||||
# rocm env
|
||||
@@ -38,9 +38,12 @@ ARG REPO=https://github.com/ggerganov/llama.cpp.git
|
||||
ARG BRANCH=master
|
||||
RUN git clone -b ${BRANCH} --single-branch --recursive ${REPO} .
|
||||
|
||||
COPY llama-grammar.patch /tmp/llama-grammar.patch
|
||||
|
||||
# build
|
||||
RUN git clean -xdf \
|
||||
&& git submodule update --recursive \
|
||||
&& patch -p1 < /tmp/llama-grammar.patch \
|
||||
&& cmake -S . -B build \
|
||||
-DGGML_HIP=ON \
|
||||
-DCMAKE_HIP_FLAGS="--rocm-path=/opt/rocm -mllvm --amdgpu-unroll-threshold-local=600" \
|
||||
|
||||
Reference in New Issue
Block a user