Merge branch 'feat/1' of github.com:skyne98/llama.cpp-gfx906 into feat/1

Author: larkinwc

.gitignore

@@ -148,4 +148,8 @@ poetry.toml
 /run-vim.sh
 /run-chat.sh
 
-.specstory
+.specstory
+
+# Model files
+models/
+*.gguf

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "ggml"]
+	path = ggml
+	url = https://github.com/skyne98/ggml-gfx906

Dockerfile.gfx906

@@ -1,9 +1,9 @@
 # Optimized Docker image for GFX906 (AMD Instinct MI50) development
-ARG ROCM_VERSION=5.7.3
+ARG ROCM_VERSION=6.2
 ARG UBUNTU_VERSION=22.04
 
 # Development base with all ROCm tools
-FROM rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION}-complete AS dev-base
+FROM rocm/dev-ubuntu-${UBUNTU_VERSION}:${ROCM_VERSION} AS dev-base
 
 # Set GFX906-specific environment
 ENV AMDGPU_TARGETS=gfx906 \

Dockerfile.gfx906-test

@@ -0,0 +1,29 @@
+# Quick test Docker image for GFX906
+FROM rocm/dev-ubuntu-22.04:6.2
+
+# Set GFX906 environment
+ENV AMDGPU_TARGETS=gfx906 \
+    HSA_OVERRIDE_GFX_VERSION=9.0.6 \
+    ROCM_PATH=/opt/rocm \
+    PATH=${ROCM_PATH}/bin:$PATH \
+    LD_LIBRARY_PATH=${ROCM_PATH}/lib:${ROCM_PATH}/lib64:$LD_LIBRARY_PATH
+
+# Install minimal dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    cmake \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /workspace
+
+# Copy the project
+COPY . /workspace/llama.cpp-gfx906/
+
+# Build the project
+WORKDIR /workspace/llama.cpp-gfx906
+RUN cmake -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=gfx906 && \
+    cmake --build build --config Release -j$(nproc)
+
+CMD ["/bin/bash"]