wmantly/turing-multi-gpu-llm-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Docs: Add cluster power optimization benchmark table and Linux headless power management guidelines

Browse Source
This commit is contained in:
wmantly
2026-09-01 19:31:56 +00:00
parent 2a21eae435
commit d51de0df6a
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/HARDWARE_LEARNINGS.md
+8
View File
@@ -25,6 +25,14 @@ Comparing the hardware profiles and the cross-flashing outcome:
* Cross-flashed GPU 1 with the MSI VBIOS ROM (`vbios/msi_cmp50hx_90.02.60.00.17.rom`) using `nvflash -6`. * Cross-flashed GPU 1 with the MSI VBIOS ROM (`vbios/msi_cmp50hx_90.02.60.00.17.rom`) using `nvflash -6`.
* **Verified Outcome**: GPU 1 idle power immediately dropped from **`61.8W` down to `31.89W`** (a **~30W direct reduction!**), and fan curve synchronized to 25% minimum floor across both cards. * **Verified Outcome**: GPU 1 idle power immediately dropped from **`61.8W` down to `31.89W`** (a **~30W direct reduction!**), and fan curve synchronized to 25% minimum floor across both cards.
### 📊 Cluster Power Optimization Benchmark Table
| Optimization State | Per-Card Draw (CMP 50HX) | RTX 2060 Draw | 3x Cluster Idle Total | Idle VRAM Temp |
| :--- | :---: | :---: | :---: | :---: |
| **Stock (Bugged VBIOS Idle)** | 75W – 85W | 11.5W | **~165W – 185W** *(240W before flash)* | ~55°C – 62°C |
| **Linux Governor (P3 Clamped @ 300MHz)** | **`31.8W – 33.7W`** | **`10.9W`** | **`~76.5W`** ⚡ *(−108W wall savings)* | **27°C – 39°C** |
| **Ideal P-State Sleep (P8 Deep Sleep)** | ~5W – 15W | ~10W | ~25W – 40W | ~25°C – 30°C |
--- ---
## 2. Power Cap vs Inference Throughput ## 2. Power Cap vs Inference Throughput