starred/nix-config-ryan4yin
1
0 Fork 0
mirror of https://github.com/ryan4yin/nix-config.git synced 2026-11-13 12:13:36 +01:00
Code Issues Packages Projects Releases 10 Wiki Activity

docs(idols-ai): record the mixed-memory freeze and current state (#433)

Browse Source 
Assisted-by: DeepSeek Harness (gpt-6.1-sol, deepseek-flash)
This commit is contained in:
ryan4yin | 二花 authored and GitHub committed 2026-10-11 20:13:06 +08:00
1 parent c347bfe6a9
commit 5c5c11d646
1 file changed
+58 -47
Download Patch File Download Diff File Expand all files Collapse all files
hosts/idols-ai/MIXED-MEMORY.md
+58 -47
View File
@@ -2,24 +2,26 @@
128G from JUHOR 2×48G + GLOWY 2×16G. All four DIMMs are needed because 96G is insufficient.
## Target configuration
## Current configuration
This is the settled configuration for normal use. It passed a **6-hour 100G stress test with 0
errors** (highest sampled memory temperature: **56.8°C**) and then **29.6 hours of daily use over
two nights and one workday**, displays on and off, LLM serving throughout. Keep these settings
rather than increasing voltage further.
CPU VDD2 is set to **1.17 V** (BIOS reads **1.168 V**). This is the best configuration tested so
far, but it still froze during daily use on 2026-10-11. Keep it for normal use for now; higher
tested VDD2 settings have not provided a stable alternative.
| Field | Target |
| ----------------------- | ------------------------- |
| XMP | Disabled |
| Gear mode | Gear2 |
| Memory speed | 4800 MT/s |
| CPU VDD2 | **1.17 V fixed** |
| VCCSA | Auto (BIOS reads 1.288 V) |
| DRAM VDD | **1.28 V fixed** |
| DRAM VDDQ | **1.28 V fixed** |
| DRAM VPP | Auto (1.8 V) |
| tCL / tRCD / tRP / tRAS | 40 / 40 / 40 / 77 |
| Field | Setting |
| ----------------------- | -------------------------------------------- |
| XMP | Disabled |
| Gear mode | Gear2 |
| Memory speed | 4800 MT/s |
| CPU VDD2 | **1.17 V fixed (BIOS reads 1.168 V)** |
| VCCSA | Auto (BIOS reads 1.288 V) |
| VDD2_MV (BIOS label) | Auto (BIOS reads 1.280 V) |
| DRAM VDD | **1.28 V fixed** |
| DRAM VDDQ | **1.28 V fixed** |
| DRAM VPP | Auto (1.8 V) |
| tCL / tRCD / tRP / tRAS | 40 / 40 / 40 / 77 (last photographed values) |
Voltage settings and readings come from BIOS and user reports, not OS measurements.
## Hardware
@@ -41,47 +43,56 @@ Earlier attempts starting with the 48G pair or all four DIMMs did not reach BIOS
2. Enter BIOS and disable XMP.
3. Power off and add the 2×48G in DIMM0.
4. Allow 1 to 3 minutes for retraining, possibly with several reboots.
5. Apply the target settings above.
5. Apply the current settings above.
If failed training prevents BIOS entry, repeat this order; clear CMOS first if necessary. Failed
training can silently restore defaults; re-check settings in BIOS afterwards.
## Test results
Earlier DRAM tests used CPU VDD2 Auto (BIOS reading 1.104 V). **Bold values identify the rails
changed in each test.**
CPU VDD2 entries below are BIOS settings: Auto read 1.104 V in the earlier DRAM tests; the 1.17 V
setting reads 1.168 V. These BIOS readings are not measurements during the OS tests.
| CPU VDD2 | DRAM VDD | DRAM VDDQ | Result | Highest sampled memory temperature |
| ---------- | ------------------------ | ------------------------ | ------------------------------------------------------------ | ---------------------------------- |
| Auto | **1.10 V** | **1.10 V** | Immediate freezes during memory tests, even 4G. | Not recorded |
| Auto | **1.25 V** | **1.25 V** | 8G / 32G / 100G short tests passed; llama.cpp load froze. | Not recorded |
| Auto | **1.28 V** | **1.28 V** | 100G short test passed; daily use froze twice on 2026-10-08. | Not recorded |
| Auto | **1.282 V** | **1.282 V** | Display corruption in BIOS. | Not recorded |
| Auto | **1.29 / 1.30 / 1.32 V** | **1.29 / 1.30 / 1.32 V** | Each setting failed training. | Not recorded |
| **1.13 V** | 1.28 V | 1.28 V | BIOS normal; no long test. | Not recorded |
| **1.15 V** | 1.28 V | 1.28 V | 100G, 15 minutes: PASS. | 45.5°C* |
| **1.15 V** | 1.28 V | 1.28 V | Long test froze; last saved duration: 21 minutes 17 seconds. | 56.5°C |
| **1.17 V** | 1.28 V | 1.28 V | 100G, **6 hours: PASS**. | **56.8°C** |
| **1.17 V** | 1.28 V | 1.28 V | **2 nights + 1 workday: no freeze**, displays on and off. | Not recorded |
| **1.20 V** | 1.28 V | 1.28 V | BIOS display corruption and freeze within 10 to 20 seconds. | Not recorded |
| CPU VDD2 | DRAM VDD | DRAM VDDQ | Result | Highest sampled DIMM temperature |
| ---------- | -------------------- | -------------------- | ------------------------------------------------------------------------------------------------------ | ---------------------------------------------- |
| Auto | 1.10 V | 1.10 V | Immediate freezes during memory tests, even 4G. | Not recorded |
| Auto | 1.25 V | 1.25 V | 8G / 32G / 100G short tests passed; llama.cpp load froze. | Not recorded |
| Auto | 1.28 V | 1.28 V | 100G short test passed; daily use froze on 2026-10-08. | Not recorded |
| Auto | 1.282 V | 1.282 V | Display corruption in BIOS. | Not recorded |
| Auto | 1.29 / 1.30 / 1.32 V | 1.29 / 1.30 / 1.32 V | Each setting failed training. | Not recorded |
| 1.13 V | 1.28 V | 1.28 V | BIOS normal; no long test. | Not recorded |
| 1.15 V | 1.28 V | 1.28 V | 100G, 15 minutes: PASS. | 45.5°C* |
| 1.15 V | 1.28 V | 1.28 V | Long test froze; last saved duration 21 min 17 s. | 56.5°C |
| **1.17 V** | **1.28 V** | **1.28 V** | **100G, 6 hours: PASS, 0 errors or hardware incidents.** | **56.8°C** |
| 1.17 V | 1.28 V | 1.28 V | About 56 hours across three boots ending cleanly; next boot froze during LLM serving (2026-10-11). | 47.2°C in the last available monitoring sample |
| 1.20 V | 1.28 V | 1.28 V | Earlier attempt: BIOS display corruption and freeze within 10 to 20 s. | Not recorded |
| 1.20 V | 1.28 V | 1.28 V | 100G test froze with screen corruption; last saved duration 7 min 23 s (2026-10-11). | 55.25°C |
| 1.18 V | 1.28 V | 1.28 V | 100G test froze with screen corruption; last saved duration 14 min 36 s (2026-10-11). | 59.5°C |
| 1.28 V | 1.28 V | 1.28 V | Reached the desktop, then froze; journal spans 16:30:16 to 16:31:20 (64 s). No recorded pressure test. | Not recorded |
| 1.30 V | 1.28 V | 1.28 V | Set in BIOS only; rolled back without booting or testing. | Not tested |
| **1.17 V** | **1.28 V** | **1.28 V** | **100G, 15 minutes: PASS, 0 errors or hardware incidents (2026-10-11 17:29–17:45).** | **59.25°C** |
*The 15-minute test used sparse temperature samples; its true peak is unknown. Long tests sampled
about every 5 seconds and used a 60°C stop threshold.
*The 1.15 V short test used sparse temperature samples; its true peak is unknown. The monitored long
tests and the 2026-10-11 100G tests sampled about every 5 seconds with a 60°C stop threshold. Saved
durations are lower bounds on time before interruption, not exact freeze times.
Both recent long tests were on 2026-10-09:
The passing 1.17 V test ran on 2026-10-09 from 01:29 to 07:30 without swap use. Subsequent daily use
included displays on and off with LLM serving. Sleep/wake is untested.
- At 1.15 V, the last record was at 01:02, with machine uptime of 1 hour 53 seconds. The saved
durations are lower bounds, not exact freeze times.
- At 1.17 V, the test ran from 01:29 to 07:30, with 0 errors or hardware incidents and no swap use.
Recorded temperatures stayed below 60°C.
The 1.17 V freeze on 2026-10-11 ended logging at 13:55:46, about 4 h 47 min after boot. Logs stopped
during generation without a shutdown sequence or a recorded machine check, BUG or Oops.
## Daily use
## BIOS limitations and conclusion
One unbroken boot, 2026-10-09 01:24 to 2026-10-10 07:02: the 6-hour test and a workday with the
displays on, then a night with them off. Load stayed high — 100G stress test, then continuous LLM
serving with the KV cache streaming from RAM — and occupancy stayed around 70% or more.
Attempts to apply tRFC 1180 and primary timings 42 / 42 / 42 / 82 reverted automatically after
saving, according to the user's BIOS checks. Those relaxed settings never became a tested
configuration. The memory frequency control is also locked at 4800 MT/s in the current BIOS setup.
The table above retains the last photographed timings; a later readback has not been recorded.
No machine check, hardware error, BUG, Oops, or GPU fall-off; no OOM or hung task; no log gap over
60 seconds. Sleep/wake is untested — displays off only blanks them. Occupancy and temperature were
not logged and the board has no EDAC counters, so an error would show up as a freeze or corruption,
not a count.
Keep CPU VDD2 at 1.17 V and DRAM VDD/VDDQ at 1.28 V for now. The passing stress test and daily-use
record make this the best tested option, but the later freeze means stability remains unresolved.
The user reports a possible ambient temperature rise of about 10°C. Temperature may affect the
remaining margin, but neither temperature nor an IMC, DIMM or motherboard fault has been isolated.
Manual timing relaxation and frequency reduction are currently unavailable; further tuning is
paused. Revisit only if freezes continue or those BIOS controls become usable.