Merge upstream llama.cpp (44 more commits, up to c08d28d)

Includes:
- server: Fix undefined timing measurement errors (ggml-org#21201)
- server: save and clear idle slots on new task --clear-idle (ggml-org#20993)
- common: fix tool call type detection for nullable/enum schemas (ggml-org#21327)
- CUDA: fix FA kernel selection logic (ggml-org#21271)
- kv-cache: do not quantize SWA KV cache (ggml-org#21277) + revert (ggml-org#21332)
- common/parser: fix call ID detection + atomicity (ggml-org#21230)
- jinja: coerce input for string-specific filters (ggml-org#21370)
- Various CI, HIP, WebGPU, and documentation fixes

Author: icex

.devops/cuda-new.Dockerfile

@@ -16,7 +16,7 @@
   rocmPackages,
   vulkan-headers,
   vulkan-loader,
-  curl,
+  openssl,
   shaderc,
   useBlas ?
     builtins.all (x: !x) [
@@ -160,7 +160,8 @@ effectiveStdenv.mkDerivation (finalAttrs: {
     ++ optionals useMpi [ mpi ]
     ++ optionals useRocm rocmBuildInputs
     ++ optionals useBlas [ blas ]
-    ++ optionals useVulkan vulkanBuildInputs;
+    ++ optionals useVulkan vulkanBuildInputs
+    ++ [ openssl ];
 
   cmakeFlags =
     [

.devops/nix/package.nix

@@ -1,8 +1,8 @@
 ARG UBUNTU_VERSION=24.04
 
 # This needs to generally match the container host's environment.
-ARG ROCM_VERSION=7.2
-ARG AMDGPU_VERSION=7.2
+ARG ROCM_VERSION=7.2.1
+ARG AMDGPU_VERSION=7.2.1
 
 # Target the ROCm build image
 ARG BASE_ROCM_DEV_CONTAINER=rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete
@@ -12,11 +12,11 @@ FROM ${BASE_ROCM_DEV_CONTAINER} AS build
 
 # Unless otherwise specified, we make a fat build.
 # This is mostly tied to rocBLAS supported archs.
-# check https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.2.0/reference/system-requirements.html
+# check https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.2.1/reference/system-requirements.html
 # check https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/compatibility/compatibilityrad/native_linux/native_linux_compatibility.html
 # check https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/compatibility/compatibilityryz/native_linux/native_linux_compatibility.html
 
-ARG ROCM_DOCKER_ARCH='gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1151;gfx1150;gfx1200;gfx1201'
+ARG ROCM_DOCKER_ARCH='gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1151;gfx1150;gfx1200;gfx1201'
 
 # Set ROCm architectures
 ENV AMDGPU_TARGETS=${ROCM_DOCKER_ARCH}

.devops/rocm.Dockerfile

@@ -27,6 +27,11 @@ IBM zDNN:
         - any-glob-to-any-file:
             - ggml/include/ggml-zdnn.h
             - ggml/src/ggml-zdnn/**
+AMD ZenDNN:
+    - changed-files:
+        - any-glob-to-any-file:
+            - ggml/include/ggml-zendnn.h
+            - ggml/src/ggml-zendnn/**
 documentation:
     - changed-files:
         - any-glob-to-any-file:

.github/labeler.yml

@@ -213,6 +213,27 @@ jobs:
           vulkaninfo --summary
           GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
 
+  ggml-ci-win-intel-vulkan:
+    runs-on: [self-hosted, Windows, X64, Intel]
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v6
+
+      - name: Test
+        id: ggml-ci
+        shell: C:\msys64\usr\bin\bash.exe --noprofile --norc -eo pipefail "{0}"
+        env:
+          MSYSTEM: UCRT64
+          CHERE_INVOKING: 1
+          PATH: C:\msys64\ucrt64\bin;C:\msys64\usr\bin;C:\Windows\System32;${{ env.PATH }}
+        run: |
+          vulkaninfo --summary
+          # Skip python related tests with GG_BUILD_LOW_PERF=1 since Windows MSYS2 UCRT64 currently fails to create
+          # a valid python environment for testing
+          LLAMA_FATAL_WARNINGS=OFF GG_BUILD_NINJA=1 GG_BUILD_VULKAN=1 GG_BUILD_LOW_PERF=1 ./ci/run.sh ./results/llama.cpp ./mnt/llama.cpp
+
   ggml-ci-intel-openvino-gpu-low-perf:
     runs-on: [self-hosted, Linux, Intel, OpenVINO]
 

.github/workflows/build-self-hosted.yml

@@ -72,7 +72,7 @@ jobs:
 
       - name: Setup Vulkan SDK
         if: steps.cache-sdk.outputs.cache-hit != 'true'
-        uses: ./.github/actions/linux-setup-vulkan-llvmpipe
+        uses: ./.github/actions/linux-setup-vulkan
         with:
           path: ./vulkan_sdk
           version: ${{ env.VULKAN_SDK_VERSION }}

.github/workflows/build-vulkan.yml

@@ -472,6 +472,7 @@ jobs:
           cmake -B build -S . \
             -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
             -DGGML_HIP_ROCWMMA_FATTN=ON \
+            -DGPU_TARGETS="gfx1030" \
             -DGGML_HIP=ON
           cmake --build build --config Release -j $(nproc)
 
@@ -941,7 +942,7 @@ jobs:
       - name: Grab rocWMMA package
         id: grab_rocwmma
         run: |
-          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70200-43~24.04_amd64.deb"
+          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb"
           7z x rocwmma.deb
           7z x data.tar
 
@@ -984,12 +985,13 @@ jobs:
           cmake -G "Unix Makefiles" -B build -S . `
             -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" `
             -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
-            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.0/include/" `
+            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/" `
             -DCMAKE_BUILD_TYPE=Release `
             -DLLAMA_BUILD_BORINGSSL=ON `
             -DROCM_DIR="${env:HIP_PATH}" `
             -DGGML_HIP=ON `
             -DGGML_HIP_ROCWMMA_FATTN=ON `
+            -DGPU_TARGETS="gfx1100"  `
             -DGGML_RPC=ON
           cmake --build build -j ${env:NUMBER_OF_PROCESSORS}
 

.github/workflows/build.yml

@@ -73,10 +73,10 @@ jobs:
             { "tag": "cpu", "dockerfile": ".devops/cpu.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04" },
             { "tag": "cpu", "dockerfile": ".devops/cpu.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04-arm" },
             { "tag": "cpu", "dockerfile": ".devops/s390x.Dockerfile", "platforms": "linux/s390x", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04-s390x" },
-            { "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
-            { "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04-arm" },
-            { "tag": "cuda13", "dockerfile": ".devops/cuda-new.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
-            { "tag": "cuda13", "dockerfile": ".devops/cuda-new.Dockerfile", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04-arm" },
+            { "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "12.8.1", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
+            { "tag": "cuda cuda12", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "12.8.1", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04-arm" },
+            { "tag": "cuda13", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "13.1.1", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
+            { "tag": "cuda13", "dockerfile": ".devops/cuda.Dockerfile", "cuda_version": "13.1.1", "platforms": "linux/arm64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04-arm" },
             { "tag": "musa", "dockerfile": ".devops/musa.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
             { "tag": "intel", "dockerfile": ".devops/intel.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": true, "runs_on": "ubuntu-24.04" },
             { "tag": "vulkan", "dockerfile": ".devops/vulkan.Dockerfile", "platforms": "linux/amd64", "full": true, "light": true, "server": true, "free_disk_space": false, "runs_on": "ubuntu-24.04" },

.github/workflows/docker.yml

@@ -35,7 +35,7 @@ env:
 jobs:
   ubuntu-22-hip-quality-check:
     runs-on: ubuntu-22.04
-    container: rocm/dev-ubuntu-22.04:7.2
+    container: rocm/dev-ubuntu-22.04:7.2.1
     steps:
       - name: Clone
         id: checkout
@@ -59,7 +59,7 @@ jobs:
         run: |
           cmake -B build -S . \
             -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
-            -DGPU_TARGETS=gfx908 \
+            -DGPU_TARGETS=gfx942 \
             -DGGML_HIP=ON \
             -DGGML_HIP_EXPORT_METRICS=Off \
             -DCMAKE_HIP_FLAGS="-Werror -Wno-tautological-compare" \

.github/workflows/hip-quality-check.yml

@@ -639,8 +639,8 @@ jobs:
     strategy:
       matrix:
         include:
-          - ROCM_VERSION: "7.2"
-            gpu_targets: "gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1151;gfx1150;gfx1200;gfx1201"
+          - ROCM_VERSION: "7.2.1"
+            gpu_targets: "gfx908;gfx90a;gfx942;gfx1030;gfx1100;gfx1101;gfx1102;gfx1151;gfx1150;gfx1200;gfx1201"
             build: 'x64'
 
     steps:
@@ -662,7 +662,7 @@ jobs:
           sudo apt install -y build-essential git cmake wget
 
       - name: Setup Legacy ROCm
-        if: matrix.ROCM_VERSION == '7.2'
+        if: matrix.ROCM_VERSION == '7.2.1'
         id: legacy_env
         run: |
           sudo mkdir --parents --mode=0755 /etc/apt/keyrings
@@ -683,7 +683,7 @@ jobs:
           sudo apt-get install -y libssl-dev rocm-hip-sdk
 
       - name: Setup TheRock
-        if: matrix.ROCM_VERSION != '7.2'
+        if: matrix.ROCM_VERSION != '7.2.1'
         id: therock_env
         run: |
           wget https://repo.amd.com/rocm/tarball/therock-dist-linux-gfx1151-${{ matrix.ROCM_VERSION }}.tar.gz
@@ -699,7 +699,6 @@ jobs:
         run: |
           cmake -B build -S . \
             -DCMAKE_HIP_COMPILER="$(hipconfig -l)/clang" \
-            -DCMAKE_HIP_FLAGS="-mllvm --amdgpu-unroll-threshold-local=600" \
             -DCMAKE_BUILD_TYPE=Release \
             -DGGML_BACKEND_DL=ON \
             -DGGML_NATIVE=OFF \
@@ -717,17 +716,20 @@ jobs:
         id: tag
         uses: ./.github/actions/get-tag-name
 
+      - name: Get ROCm short version
+        run: echo "ROCM_VERSION_SHORT=$(echo '${{ matrix.ROCM_VERSION }}' | cut -d '.' -f 1,2)" >> $GITHUB_ENV
+
       - name: Pack artifacts
         id: pack_artifacts
         run: |
           cp LICENSE ./build/bin/
-          tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
+          tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
 
       - name: Upload artifacts
         uses: actions/upload-artifact@v6
         with:
-          path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}.tar.gz
-          name: llama-bin-ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}.tar.gz
+          path: llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.tar.gz
+          name: llama-bin-ubuntu-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.tar.gz
 
   windows-hip:
     runs-on: windows-2022
@@ -749,7 +751,7 @@ jobs:
       - name: Grab rocWMMA package
         id: grab_rocwmma
         run: |
-          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70200-43~24.04_amd64.deb"
+          curl -o rocwmma.deb "https://repo.radeon.com/rocm/apt/7.2.1/pool/main/r/rocwmma-dev/rocwmma-dev_2.2.0.70201-81~24.04_amd64.deb"
           7z x rocwmma.deb
           7z x data.tar
 
@@ -806,7 +808,7 @@ jobs:
           cmake -G "Unix Makefiles" -B build -S . `
             -DCMAKE_C_COMPILER="${env:HIP_PATH}\bin\clang.exe" `
             -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
-            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.0/include/ -Wno-ignored-attributes -Wno-nested-anon-types" `
+            -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-7.2.1/include/ -Wno-ignored-attributes -Wno-nested-anon-types" `
             -DCMAKE_BUILD_TYPE=Release `
             -DGGML_BACKEND_DL=ON `
             -DGGML_NATIVE=OFF `