julian/amd-strix-halo-toolboxes
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Added github bug for rocm model loading

Browse Source
This commit is contained in:
Donato Capitella
2025-08-01 19:28:58 +01:00
parent f17720ca55
commit 6f001d2a05
1 changed files with 14 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+5 -2
View File
@@ -32,7 +32,7 @@ Fedora Rawhide-based containers for AMD Ryzen AI MAX+ 395 **Strix Halo** chips w
| Backend | Status | Notes |
|---------|---------|-------|
| **Vulkan** | ✅ **Recommended** | Most stable, best performance across all model sizes |
| **ROCm 6.4.2** | ⚠️ Limited | Works ok, but extremely slow past 64GB memory allocations |
| **ROCm 6.4.2** | ⚠️ Limited | Works ok, but extremely slow past 64GB memory allocations [GitHub Issue #15018](https://github.com/ggml-org/llama.cpp/issues/15018) |
| **ROCm 7.0 beta** | ❌ Unstable | Frequent crashes under heavy load (llama-bench), basic usage possible |
## 2. Available Containers
@@ -70,7 +70,8 @@ podman pull docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-7beta
**For Vulkan (Recommended):**
```bash
toolbox create llama-vulkan \
--image docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan \
--image docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan \[GitHub Issue #15018](https://github.com/ggml-org/llama.cpp/issues/15018)
-- \
--device /dev/dri \
--group-add video \
@@ -327,3 +328,5 @@ sudo reboot
Follow this guide by TechnigmaAI for a working configuration on Ubuntu 22.04:
https://github.com/technigmaai/technigmaai-wiki/wiki/AMD-Ryzen-AI-Max--395:-GTT--Memory-Step%E2%80%90by%E2%80%90Step-Instructions-(Ubuntu-24.04)