Adding rocm-6.4.3 to README and to refresh script. Adding hipBLASLt.

README.md

@@ -49,11 +49,13 @@ You can check the containers on DockerHub: https://hub.docker.com/r/kyuz0/amd-st
 | `vulkan-radv`        | Vulkan (Mesa RADV)        | Most stable and compatible. Recommended for most users and all models. |
 | `rocm-6.4.2`         | ROCm 6.4.2 (HIP)          | Latest stable ROCm. Great for BF16 models. Occasional crashes possible. |
 | `rocm-6.4.2-rocwmma` | ROCm 6.4.2 (HIP) + ROCWMMA | ROCm with ROCWMMA enabled for improved flash attention on RDNA3+/CDNA. |
+| `rocm-6.4.3`         | ROCm 6.4.3 (HIP) + hipBLASLt*          | Latest stable ROCm. Great for BF16 models. Occasional crashes possible. |
+| `rocm-6.4.3-rocwmma` | ROCm 6.4.3 (HIP) + ROCWMMA + hipBLASLt*  | ROCm with ROCWMMA enabled for improved flash attention on RDNA3+/CDNA. |
 | `rocm-7beta`         | ROCm 7.0 Beta (HIP) + hipBLASLt*      | Latest ROCm beta. No real gain for Llama.cpp. Same model limits as 6.4.2. |
 | `rocm-7rc`           | ROCm 7.0 RC (HIP) + hipBLASLt*         | Release candidate for ROCm 7.0. Same behavior as beta. |
 | `rocm-7rc-rocwmma`   | ROCm 7.0 RC (HIP) + ROCWMMA + hipBLASLt*       | Release candidate for ROCm 7.0, with hipBLASLt and ROCWMMA for improved flash attention on RDNA3+/CDNA |
 
-* All ROCm 7 toolboxes now export `ROCBLAS_USE_HIPBLASLT=1` as this currently results in better perfromance and stability.
+\* All these toolboxes now export `ROCBLAS_USE_HIPBLASLT=1` as this currently results in better perfromance and stability in *MOST* cases.
 
 > These containers are **automatically** rebuilt whenever the Llama.cpp master branch is updated, ensuring you get the latest bug fixes and new model support. The easiest way to update to the newest versions is by running the `refresh-toolboxes.sh` [script below](#211-toolbox-refresh-script-automatic-updates).
 

refresh-toolboxes.sh

@@ -9,6 +9,8 @@ TOOLBOXES["llama-vulkan-amdvlk"]="docker.io/kyuz0/amd-strix-halo-toolboxes:vulka
 TOOLBOXES["llama-vulkan-radv"]="docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv --device /dev/dri --group-add video --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-6.4.2"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-6.4.2 --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-6.4.2-rocwmma"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-6.4.2-rocwmma --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
+TOOLBOXES["llama-rocm-6.4.3"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-6.4.3 --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
+TOOLBOXES["llama-rocm-6.4.3-rocwmma"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-6.4.3-rocwmma --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-7beta"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7beta --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-7rc"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7rc --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"
 TOOLBOXES["llama-rocm-7rc-rocwmma"]="docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7rc-rocwmma --device /dev/dri --device /dev/kfd --group-add video --group-add render --group-add sudo --security-opt seccomp=unconfined"

toolboxes/Dockerfile.rocm-6.4.3

@@ -45,6 +45,12 @@ RUN git clean -xdf \
 RUN find /opt/llama.cpp/build -type f -name 'lib*.so*' -exec cp {} /usr/lib64/ \; \
  && ldconfig
 
+RUN printf '%s\n' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
 COPY gguf-vram-estimator.py /usr/local/bin/gguf-vram-estimator.py
 RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
 

toolboxes/Dockerfile.rocm-6.4.3-rocwmma

@@ -55,5 +55,11 @@ RUN find /opt/llama.cpp/build -type f -name 'lib*.so*' -exec cp {} /usr/lib64/ \
 COPY gguf-vram-estimator.py /usr/local/bin/gguf-vram-estimator.py
 RUN chmod +x /usr/local/bin/gguf-vram-estimator.py
 
+RUN printf '%s\n' \
+  'export ROCBLAS_USE_HIPBLASLT=1' \
+  > /etc/profile.d/rocm.sh \
+  && chmod +x /etc/profile.d/rocm.sh \
+  && echo 'source /etc/profile.d/rocm.sh' >> /etc/bashrc
+
 # Default to interactive shell
 CMD ["/bin/bash"]