dank/serverAppConfigs
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

docs: correct Dankclaw RAM figure (64 GiB, 61 GiB visible)

Browse Source 
The box was upgraded from 32 GB to 64 GB. Two vLLM sizing pages
still stated 30 GiB physical RAM; rocm-smi reports 64 GiB and free
shows 61 GiB visible. Update the hardware tables and the ROCm
overcommit guidance to match.

Also removes the vllm-vulkan backend page, its index links, and the
frank-vk-compat plugin from the working tree. The vLLM service on
Dankclaw is being retired in favor of the CIRU llama.cpp runtime.
This commit is contained in:
Frank
2026-08-17 20:34:51 -07:00
parent 044dd49011
commit 4941d911f2
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/Running Qwen3.6 27B FP8 on Dankclaw.md
+2 -2
View File
@@ -26,7 +26,7 @@ Qwen3.6-27B is a dense vision-language model from the Qwen3.6 series. It uses 27
|----------|-------|
| CPU | AMD RYZEN AI MAX+ 395 w/ Radeon 8060S (Strix Halo) |
| GPU | Integrated Radeon 8060S (unified memory) |
| Physical RAM | 30 GiB (shared CPU + GPU) |
| Physical RAM | 64 GiB (61 GiB visible; corrected 2026-08-17) |
| GPU-Visible (ROCm) | 96 GiB (overcommitted) |
| Swap | 8 GiB |
| ROCm | 7.2.4 |
@@ -43,7 +43,7 @@ Qwen3.6-27B is a dense vision-language model from the Qwen3.6 series. It uses 27
| Overhead | ~2 GB | ~2 GB |
| **Total (approximate)** | ~58 GB | ~16.5 GB |
The FP8 variant requires approximately 16-17 GB. ThinkingCap-FP8 requires ~29 GB. Both fit within the 30 GiB physical RAM, but ROCm reports 96 GiB to vLLM. Set `--gpu-memory-utilization` conservatively (0.80) to avoid OOM.
The FP8 variant requires approximately 16-17 GB. ThinkingCap-FP8 requires ~29 GB. Both fit within the 61 GiB physical RAM, but ROCm reports 96 GiB to vLLM. Set `--gpu-memory-utilization` conservatively (0.80) to avoid OOM.
## Prerequisites
docs/Shared Memory Architecture Dankclaw.md
+1 -1
View File
@@ -142,7 +142,7 @@ Unified memory has lower bandwidth than dedicated VRAM:
### ROCm Overcommit
ROCm reports 96 GiB GPU memory on Strix Halo APU. Physical RAM is 30 GiB. The GPU can address more than physical RAM exists. vLLM will see 96 GiB and try to allocate accordingly. Set `--gpu-memory-utilization` to 0.80 or lower to prevent OOM.
ROCm reports 96 GiB GPU memory on Strix Halo APU. Physical RAM is 64 GiB (61 GiB visible; corrected 2026-08-17, the box was upgraded from 32 GB). The GPU can address more than physical RAM exists. vLLM will see 96 GiB and try to allocate accordingly. Set `--gpu-memory-utilization` to 0.80 or lower to prevent OOM.
Lower bandwidth means slower inference. Plan for lower throughput.