hermes
7f3096e86e
- 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.
30 lines
910 B
YAML
30 lines
910 B
YAML
services:
|
|
qwen38-flash-next:
|
|
build: .
|
|
image: haloq38flash:latest
|
|
container_name: qwen38-flash-next
|
|
devices:
|
|
- /dev/dri
|
|
group_add:
|
|
- video
|
|
- render
|
|
security_opt:
|
|
- seccomp=unconfined
|
|
volumes:
|
|
- /mnt/ssd2/models/qwen38-flash-next:/models:ro
|
|
ports:
|
|
- "8080:8080"
|
|
environment:
|
|
- LD_LIBRARY_PATH=/app
|
|
# the image CMD is bare (/app/llama-server) — pass the model + flags:
|
|
command: >-
|
|
-m /models/Qwen3.8-Flash-Next-IQ4_XS-PLE.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
|