diff --git a/.devops/llama-cli-cann.Dockerfile b/.devops/llama-cli-cann.Dockerfile index db5ba2f25..45c0585b0 100644 --- a/.devops/llama-cli-cann.Dockerfile +++ b/.devops/llama-cli-cann.Dockerfile @@ -1,6 +1,6 @@ ARG ASCEND_VERSION=8.0.rc2.alpha003-910b-openeuler22.03-py3.8 -FROM cosdt/cann:$ASCEND_VERSION AS build +FROM ascendai/cann:$ASCEND_VERSION AS build WORKDIR /app @@ -26,7 +26,7 @@ RUN echo "Building with static libs" && \ cmake --build build --config Release --target llama-cli # TODO: use image with NNRT -FROM cosdt/cann:$ASCEND_VERSION AS runtime +FROM ascendai/cann:$ASCEND_VERSION AS runtime COPY --from=build /app/build/bin/llama-cli /llama-cli ENV LC_ALL=C.utf8 diff --git a/.devops/llama-cli-intel.Dockerfile b/.devops/llama-cli-intel.Dockerfile index 79dba06a7..1f4ce0730 100644 --- a/.devops/llama-cli-intel.Dockerfile +++ b/.devops/llama-cli-intel.Dockerfile @@ -1,4 +1,4 @@ -ARG ONEAPI_VERSION=2024.1.1-devel-ubuntu22.04 +ARG ONEAPI_VERSION=2025.0.0-0-devel-ubuntu22.04 FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build diff --git a/.devops/llama-server-intel.Dockerfile b/.devops/llama-server-intel.Dockerfile index 9c355b664..773f030a7 100644 --- a/.devops/llama-server-intel.Dockerfile +++ b/.devops/llama-server-intel.Dockerfile @@ -1,4 +1,4 @@ -ARG ONEAPI_VERSION=2024.1.1-devel-ubuntu22.04 +ARG ONEAPI_VERSION=2025.0.0-0-devel-ubuntu22.04 FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index c770bbd15..6ef0770f3 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -414,6 +414,27 @@ jobs: cmake -B build2 -S . -DCMAKE_C_COMPILER=hipcc -DCMAKE_CXX_COMPILER=hipcc -DGGML_HIP=ON cmake --build build2 --config Release -j $(nproc) + ubuntu-22-cmake-musa: + runs-on: ubuntu-22.04 + container: mthreads/musa:rc3.1.0-devel-ubuntu22.04 + + steps: + - name: Clone + id: checkout + uses: actions/checkout@v4 + + - name: Dependencies + id: depends + run: | + apt-get update + apt-get install -y build-essential git cmake libcurl4-openssl-dev + + - name: Build with native CMake MUSA support + id: cmake_build + run: | + cmake -B build -S . -DGGML_MUSA=ON + cmake --build build --config Release -j $(nproc) + ubuntu-22-cmake-sycl: runs-on: ubuntu-22.04 diff --git a/docs/build.md b/docs/build.md index 95512415a..52de2b4e2 100644 --- a/docs/build.md +++ b/docs/build.md @@ -375,7 +375,7 @@ cmake --build build --config release You can test with: -`./build/llama-cli -m PATH_TO_MODEL -p "Building a website can be done in 10 steps:" -ngl 32` +`./build/bin/llama-cli -m PATH_TO_MODEL -p "Building a website can be done in 10 steps:" -ngl 32` If the fllowing info is output on screen, you are using `llama.cpp by CANN backend`: ```bash diff --git a/examples/server/public/index.html b/examples/server/public/index.html index e636f770c..fd41ed493 100644 --- a/examples/server/public/index.html +++ b/examples/server/public/index.html @@ -12,7 +12,7 @@ .markdown { h1, h2, h3, h4, h5, h6, ul, ol, li { all: revert; } pre { - @apply whitespace-pre-wrap my-4 rounded-lg p-2; + @apply whitespace-pre-wrap rounded-lg p-2; border: 1px solid currentColor; } /* TODO: fix markdown table */ @@ -25,8 +25,11 @@ .bg-base-200 {background-color: var(--fallback-b2,oklch(var(--b2)/1))} .bg-base-300 {background-color: var(--fallback-b3,oklch(var(--b3)/1))} .text-base-content {color: var(--fallback-bc,oklch(var(--bc)/1))} + .show-on-hover { + @apply opacity-0 group-hover:opacity-100; + } .btn-mini { - @apply cursor-pointer opacity-0 group-hover:opacity-100 hover:shadow-md; + @apply cursor-pointer hover:shadow-md; } .chat-screen { max-width: 900px; } /* because the default bubble color is quite dark, we will make a custom one using bg-base-300 */ @@ -152,14 +155,14 @@
- - -
@@ -196,12 +199,13 @@

Settings

Settings below are saved in browser's localStorage

+ @@ -209,7 +213,7 @@ Other sampler settings
@@ -218,7 +222,7 @@ Penalties settings
@@ -254,7 +258,7 @@
-