Temp

.clang-tidy

@@ -17,8 +17,10 @@ Checks: >
     -clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling,
     performance-*,
     portability-*,
+    -portability-simd-intrinsics,
     misc-*,
     -misc-const-correctness,
     -misc-non-private-member-variables-in-classes,
     -misc-no-recursion,
+    -misc-use-anonymous-namespace,
 FormatStyle: none

.devops/full-musa.Dockerfile

@@ -6,6 +6,9 @@ ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_V
 
 FROM ${BASE_MUSA_DEV_CONTAINER} AS build
 
+# MUSA architecture to build for (defaults to all supported archs)
+ARG MUSA_DOCKER_ARCH=default
+
 RUN apt-get update && \
     apt-get install -y build-essential cmake python3 python3-pip git libcurl4-openssl-dev libgomp1
 
@@ -19,7 +22,11 @@ WORKDIR /app
 
 COPY . .
 
-RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
+# Use the default MUSA archs if not specified
+RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
+        export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
+    fi && \
+    cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
     cmake --build build --config Release -j$(nproc) && \
     cp build/bin/* .
 

.devops/llama-cli-musa.Dockerfile

@@ -8,14 +8,21 @@ ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU
 
 FROM ${BASE_MUSA_DEV_CONTAINER} AS build
 
+# MUSA architecture to build for (defaults to all supported archs)
+ARG MUSA_DOCKER_ARCH=default
+
 RUN apt-get update && \
     apt-get install -y build-essential git cmake
 
 WORKDIR /app
 
 COPY . .
 
-RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
+# Use the default MUSA archs if not specified
+RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
+        export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
+    fi && \
+    cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
     cmake --build build --config Release --target llama-cli -j$(nproc) && \
     mkdir -p /app/lib && \
     find build -name "*.so" -exec cp {} /app/lib \;

.devops/llama-server-musa.Dockerfile

@@ -8,14 +8,21 @@ ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU
 
 FROM ${BASE_MUSA_DEV_CONTAINER} AS build
 
+# MUSA architecture to build for (defaults to all supported archs)
+ARG MUSA_DOCKER_ARCH=default
+
 RUN apt-get update && \
     apt-get install -y build-essential git cmake libcurl4-openssl-dev
 
 WORKDIR /app
 
 COPY . .
 
-RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
+# Use the default MUSA archs if not specified
+RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
+        export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
+    fi && \
+    cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
     cmake --build build --config Release --target llama-server -j$(nproc) && \
     mkdir -p /app/lib && \
     find build -name "*.so" -exec cp {} /app/lib \;

.devops/nix/python-scripts.nix

@@ -34,7 +34,7 @@ let
 
     # server tests
     openai
-    behave
+    pytest
     prometheus-client
   ];
 in

.github/ISSUE_TEMPLATE/010-bug-compilation.yml

@@ -24,7 +24,8 @@ body:
   - type: dropdown
     id: operating-system
     attributes:
-      label: Which operating systems do you know to be affected?
+      label: Operating systems
+      description: Which operating systems do you know to be affected?
       multiple: true
       options:
         - Linux
@@ -41,14 +42,17 @@ body:
         description: Which GGML backends do you know to be affected?
         options: [AMX, BLAS, CPU, CUDA, HIP, Kompute, Metal, Musa, RPC, SYCL, Vulkan]
         multiple: true
+    validations:
+      required: true
   - type: textarea
-    id: steps_to_reproduce
+    id: info
     attributes:
-      label: Steps to Reproduce
+      label: Problem description & steps to reproduce
       description: >
-        Please tell us how to reproduce the bug and any additional information that you think could be useful for fixing it.
+        Please give us a summary of the problem and tell us how to reproduce it.
         If you can narrow down the bug to specific compile flags, that information would be very much appreciated by us.
       placeholder: >
+        I'm trying to compile llama.cpp with CUDA support on a fresh install of Ubuntu and get error XY.
         Here are the exact commands that I used: ...
     validations:
       required: true

.github/ISSUE_TEMPLATE/011-bug-results.yml

@@ -26,7 +26,8 @@ body:
   - type: dropdown
     id: operating-system
     attributes:
-      label: Which operating systems do you know to be affected?
+      label: Operating systems
+      description: Which operating systems do you know to be affected?
       multiple: true
       options:
         - Linux
@@ -43,6 +44,8 @@ body:
         description: Which GGML backends do you know to be affected?
         options: [AMX, BLAS, CPU, CUDA, HIP, Kompute, Metal, Musa, RPC, SYCL, Vulkan]
         multiple: true
+    validations:
+      required: true
   - type: textarea
     id: hardware
     attributes:
@@ -55,20 +58,20 @@ body:
   - type: textarea
     id: model
     attributes:
-      label: Model
+      label: Models
       description: >
-        Which model at which quantization were you using when encountering the bug?
+        Which model(s) at which quantization were you using when encountering the bug?
         If you downloaded a GGUF file off of Huggingface, please provide a link.
       placeholder: >
         e.g. Meta LLaMA 3.1 Instruct 8b q4_K_M
     validations:
       required: false
   - type: textarea
-    id: steps_to_reproduce
+    id: info
     attributes:
-      label: Steps to Reproduce
+      label: Problem description & steps to reproduce
       description: >
-        Please tell us how to reproduce the bug and any additional information that you think could be useful for fixing it.
+        Please give us a summary of the problem and tell us how to reproduce it.
         If you can narrow down the bug to specific hardware, compile flags, or command line arguments,
         that information would be very much appreciated by us.
       placeholder: >

.github/ISSUE_TEMPLATE/019-bug-misc.yml

@@ -14,7 +14,7 @@ body:
     id: version
     attributes:
       label: Name and Version
-      description: Which version of our software are you running? (use `--version` to get a version string)
+      description: Which version of our software is affected? (You can use `--version` to get a version string.)
       placeholder: |
         $./llama-cli --version
         version: 2999 (42b4109e)
@@ -24,7 +24,8 @@ body:
   - type: dropdown
     id: operating-system
     attributes:
-      label: Which operating systems do you know to be affected?
+      label: Operating systems
+      description: Which operating systems do you know to be affected?
       multiple: true
       options:
         - Linux
@@ -33,36 +34,38 @@ body:
         - BSD
         - Other? (Please let us know in description)
     validations:
-      required: true
+      required: false
   - type: dropdown
     id: module
     attributes:
       label: Which llama.cpp modules do you know to be affected?
       multiple: true
       options:
+        - Documentation/Github
         - libllama (core library)
         - llama-cli
         - llama-server
         - llama-bench
         - llama-quantize
         - Python/Bash scripts
+        - Test code
         - Other (Please specify in the next section)
     validations:
-      required: true
+      required: false
   - type: textarea
-    id: steps_to_reproduce
+    id: info
     attributes:
-      label: Steps to Reproduce
+      label: Problem description & steps to reproduce
       description: >
-        Please tell us how to reproduce the bug and any additional information that you think could be useful for fixing it.
+        Please give us a summary of the problem and tell us how to reproduce it (if applicable).
     validations:
       required: true
   - type: textarea
     id: first_bad_commit
     attributes:
       label: First Bad Commit
       description: >
-        If the bug was not present on an earlier version: when did it start appearing?
+        If the bug was not present on an earlier version and it's not trivial to track down: when did it start appearing?
         If possible, please do a git bisect and identify the exact commit that introduced the bug.
     validations:
       required: false
@@ -71,8 +74,8 @@ body:
     attributes:
       label: Relevant log output
       description: >
-          Please copy and paste any relevant log output, including the command that you entered and any generated text.
+          If applicable, please copy and paste any relevant log output, including the command that you entered and any generated text.
           This will be automatically formatted into code, so no need for backticks.
       render: shell
     validations:
-      required: true
+      required: false

.github/labeler.yml

@@ -3,19 +3,18 @@ Kompute:
     - changed-files:
         - any-glob-to-any-file:
             - ggml/include/ggml-kompute.h
-            - ggml/src/ggml-kompute.cpp
+            - ggml/src/ggml-kompute/**
             - README-kompute.md
 Apple Metal:
     - changed-files:
         - any-glob-to-any-file:
             - ggml/include/ggml-metal.h
-            - ggml/src/ggml-metal.cpp
+            - ggml/src/ggml-metal/**
             - README-metal.md
 SYCL:
     - changed-files:
         - any-glob-to-any-file:
             - ggml/include/ggml-sycl.h
-            - ggml/src/ggml-sycl.cpp
             - ggml/src/ggml-sycl/**
             - docs/backend/SYCL.md
             - examples/sycl/**
@@ -27,8 +26,8 @@ Nvidia GPU:
 Vulkan:
     - changed-files:
         - any-glob-to-any-file:
-            - ggml/ggml_vk_generate_shaders.py
-            - ggml/src/ggml-vulkan*
+            - ggml/include/ggml-vulkan.h
+            - ggml/src/ggml-vulkan/**
 documentation:
     - changed-files:
         - any-glob-to-any-file:
@@ -75,11 +74,7 @@ server:
 ggml:
     - changed-files:
         - any-glob-to-any-file:
-            - ggml/include/ggml*.h
-            - ggml/src/ggml*.c
-            - ggml/src/ggml*.cpp
-            - ggml/src/ggml*.h
-            - ggml-cuda/**
+            - ggml/**
 nix:
     - changed-files:
         - any-glob-to-any-file: