fix: bump llama.cpp from b9596 to b9890 for slot/stability fixes

b9596 (Dec 2024) has known slot deadlock on first request causing
container freeze. b9890 includes:
- Slot selection consolidation (#24755)
- HIP fast-math support (#23862)
- Hundreds of stability and memory fixes

Compatible with ROCm 6.1 + gfx906 (same build flags).
This commit is contained in:
2026-07-07 16:57:16 -04:00
parent 2d2787f404
commit 5db33ddfd2

View File

@@ -1,10 +1,12 @@
# llama-cpp-rocm6/Dockerfile # llama-cpp-rocm6/Dockerfile
# Custom llama.cpp server with ROCm 6.1 + gfx906 (MI50) support. # Custom llama.cpp server with ROCm 6.1 + gfx906 (MI50) support.
# Build: docker build -t llama-cpp:rocm-gfx906 . # Build: docker build -t llama-cpp:rocm-gfx906 .
# NOTE: Update LLAMACPP_VERSION for bugfixes, but verify ROCm 6.1 compat
# by checking if recent releases still support -DGGML_HIP=ON.
FROM rocm/dev-ubuntu-22.04:6.1.2-complete AS builder FROM rocm/dev-ubuntu-22.04:6.1.2-complete AS builder
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y curl git build-essential pkg-config cmake make && rm -rf /var/lib/apt/lists/* RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y curl git build-essential pkg-config cmake make && rm -rf /var/lib/apt/lists/*
ARG LLAMACPP_VERSION=b9596 ARG LLAMACPP_VERSION=b9890
RUN git clone --depth 1 --branch ${LLAMACPP_VERSION} https://github.com/ggml-org/llama.cpp.git /build RUN git clone --depth 1 --branch ${LLAMACPP_VERSION} https://github.com/ggml-org/llama.cpp.git /build
WORKDIR /build WORKDIR /build
ENV HIP_PATH=/opt/rocm ROCM_PATH=/opt/rocm PATH=/opt/rocm/bin:/opt/rocm/llvm/bin:${PATH} CMAKE_PREFIX_PATH=/opt/rocm ENV HIP_PATH=/opt/rocm ROCM_PATH=/opt/rocm PATH=/opt/rocm/bin:/opt/rocm/llvm/bin:${PATH} CMAKE_PREFIX_PATH=/opt/rocm