Dockerfile: fix build on ubuntu 24.04

- ppa:kisak/kisak does not exist (repo is kisak-mesa) and add-apt-repository
  failed outright; noble-updates already ships mesa 25.2.x with gfx1151 radv,
  so drop the PPA and use the distro mesa
- pin a modern shaderc/glslc (v2026.3) from conda-forge: noble's glslc
  (shaderc 2023.8) predates GL_NV_cooperative_matrix2 and the fork's
  coopmat2 vulkan kernels; the pinned stack is self-contained (rpath)
- add missing build deps this fork needs: pkg-config, spirv-headers
  (find_package(SPIRV-Headers) in ggml-vulkan), libssl-dev (httplib TLS),
  unzip/zstd for the glslc bundle
- copy all shared libs from bin/ (fork produces libmtmd, *-impl libs and
  backend .so's the old glob missed) + register /app via ld.so.conf
- drop LLAMA_CURL (deprecated no-op in this fork)
- CMD is now bare /app/llama-server so the image can be driven by an
  external runtime (llamaswap); host/port stay overridable via
  LLAMA_ARG_HOST/LLAMA_ARG_PORT env. compose passes the recommended flags

Verified by a clean-room build of the strix-halo-vulkan branch with
noble's toolchain + headers (gcc 13, vulkan-headers 1.3.275, openssl 3.0.13):
all three targets link and resolve against stock noble runtime libs,
llama-server/cli/bench boot successfully.

Dockerfile

@@ -1,21 +1,48 @@
 # haloq38flash — qwen3.8-flash-next on strix halo (vulkan/radv)
 # builds the nathanw1014 strix-halo-vulkan engine and serves with the
 # recommended flags. models are mounted, not baked in.
+#
+# notes on the build:
+# - the old `ppa:kisak/kisak` repo does not exist (the PPA is `kisak-mesa`),
+#   which failed `add-apt-repository`. noble-updates already ships
+#   mesa 25.2.x (radv supports gfx1151), so no PPA is needed.
+# - noble's glslc (shaderc 2023.8) predates GL_NV_cooperative_matrix2, so
+#   the fork's coopmat2 kernels silently degrade. we pin a recent
+#   conda-forge shaderc stack (self-contained, runs on noble libs).
+# - LLAMA_CURL is a deprecated no-op option in this fork; dropped.
+# - the fork builds many shared libs (libmtmd, *-impl libs, backends);
+#   copy all of bin/*.so*, not just libggml*/libllama*.
 
 # ---- stage 1: build ----
 FROM ubuntu:24.04 AS build
 ENV DEBIAN_FRONTEND=noninteractive
-RUN apt-get update && apt-get install -y \
+RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential cmake ninja-build git ccache \
+    build-essential cmake ninja-build git ccache pkg-config \
-    libvulkan-dev glslc vulkan-tools \
+    ca-certificates curl unzip zstd \
-    libcurl4-openssl-dev \
+    libvulkan-dev spirv-headers libssl-dev \
     && rm -rf /var/lib/apt/lists/*
 
+# modern glslc (shaderc v2026.3) + its libs, pinned conda-forge builds.
+# glslc uses rpath $ORIGIN/../lib, so /opt/glslc/{bin,lib} is self-contained.
+RUN set -eux; \
+    mkdir -p /opt/glslc /tmp/gc; cd /tmp/gc; \
+    for u in \
+      https://conda.anaconda.org/conda-forge/linux-64/shaderc-2026.3-hcebf71c_1.conda \
+      https://conda.anaconda.org/conda-forge/linux-64/glslang-16.5.0-h980caa0_2.conda \
+      https://conda.anaconda.org/conda-forge/linux-64/spirv-tools-2026.3-h7148c6a_1.conda; do \
+        curl -fL --retry 3 -o pkg.conda "$u"; \
+        unzip -o -q pkg.conda "pkg-*.tar.zst"; \
+        tar --zstd -xf pkg-*.tar.zst -C /opt/glslc; \
+        rm -f pkg.conda pkg-*.tar.zst; \
+    done; \
+    rm -rf /tmp/gc; \
+    /opt/glslc/bin/glslc --version | head -1
+
 RUN git clone --depth 1 -b strix-halo-vulkan \
     https://github.com/Nathanw1014/llama.cpp /src/engine
-RUN cmake -B /src/engine/build -S /src/engine \
+RUN cmake -B /src/engine/build -S /src/engine -G Ninja \
     -DCMAKE_BUILD_TYPE=Release -DGGML_VULKAN=ON \
-    -DLLAMA_CURL=ON \
+    -DVulkan_GLSLC_EXECUTABLE=/opt/glslc/bin/glslc \
     && cmake --build /src/engine/build --parallel $(nproc) \
        --target llama-server llama-cli llama-bench
 
@@ -23,22 +50,24 @@ RUN cmake -B /src/engine/build -S /src/engine \
 FROM ubuntu:24.04
 ENV DEBIAN_FRONTEND=noninteractive
 
-# add kisak ppa for recent mesa/radv (gfx1151 needs >= 24.x)
+# stock noble mesa (25.2.x in noble-updates) — radv gfx1151 supported,
-RUN apt-get update && apt-get install -y software-properties-common gpg-agent \
+# no PPA needed
-    && add-apt-repository -y ppa:kisak/kisak \
+RUN apt-get update && apt-get install -y --no-install-recommends \
-    && apt-get update && apt-get install -y \
     mesa-vulkan-drivers vulkan-tools libvulkan1 \
-    libcurl4 \
+    libssl3t64 libgomp1 libstdc++6 ca-certificates \
     && rm -rf /var/lib/apt/lists/*
 
 COPY --from=build /src/engine/build/bin/llama-server /app/llama-server
 COPY --from=build /src/engine/build/bin/llama-cli /app/llama-cli
 COPY --from=build /src/engine/build/bin/llama-bench /app/llama-bench
-COPY --from=build /src/engine/build/bin/libggml*.so* /app/
+COPY --from=build /src/engine/build/bin/ /tmp/engine-bin/
-COPY --from=build /src/engine/build/bin/libllama*.so* /app/
+RUN set -eux; \
-
+    for f in /tmp/engine-bin/*.so*; do \
-RUN ldconfig /app 2>/dev/null; true
+      [ -e "$f" ] || continue; \
-ENV LD_LIBRARY_PATH=/app
+      if [ -L "$f" ]; then cp -a "$f" /app/; else cp -aL "$f" /app/; fi; \
+    done; \
+    rm -rf /tmp/engine-bin; \
+    echo /app > /etc/ld.so.conf.d/app.conf; ldconfig
 
 # models volume
 VOLUME /models
@@ -46,9 +75,9 @@ VOLUME /models
 WORKDIR /app
 EXPOSE 8080
 
-CMD ["/app/llama-server", \
+# bare binary — pass all args (model, ctx, spec decode, ...) from the
-     "-m", "/models/Qwen3.8-Flash-Next-IQ4_XS-PLE.gguf", \
+# container runtime / llamaswap. bind defaults kept env-configurable:
-     "-ngl", "999", "-fa", "on", \
+# override with -e LLAMA_ARG_HOST=... / -e LLAMA_ARG_PORT=...
-     "-ctk", "q8_0", "-ctv", "q8_0", \
+ENV LLAMA_ARG_HOST=0.0.0.0 \
-     "-c", "32768", "-ub", "2048", "-t", "4", \
+    LLAMA_ARG_PORT=8080
-     "--jinja", "--host", "0.0.0.0", "--port", "8080"]
+CMD ["/app/llama-server"]

docker-compose.yml

@@ -16,8 +16,14 @@ services:
       - "8080:8080"
     environment:
       - LD_LIBRARY_PATH=/app
-    # override CMD to change context, quant, or add mtp:
+    # the image CMD is bare (/app/llama-server) — pass the model + flags:
-    # docker compose run qwen38-flash-next \
+    command: >-
-    #   /app/llama-server -m /models/Qwen3.8-Flash-Next-IQ4_XS-PLE.gguf \
+      -m /models/Qwen3.8-Flash-Next-IQ4_XS-PLE.gguf
-    #   -c 131072 -md /models/mtp-Qwen3.8-Flash-Next-Q8_0.gguf \
+      -ngl 999 -fa on -ctk q8_0 -ctv q8_0
+      -c 32768 -ub 2048 -t 4 --jinja
+    # for mtp speculative decoding:
+    # command: >-
+    #   -m /models/Qwen3.8-Flash-Next-IQ4_XS-PLE.gguf
+    #   -md /models/mtp-Qwen3.8-Flash-Next-Q8_0.gguf
     #   --spec-type draft-mtp --spec-draft-n-max 6 --spec-draft-p-min 0.75
+    #   -ngl 999 -fa on -ctk q8_0 -ctv q8_0 -c 32768 -ub 2048 -t 4 --jinja