Skip to content

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

C++

docs/TROUBLESHOOTING.md: the Windows AMD driver-reset entry is back

Niko1221f06bfc30e759
diff --git a/docs/TROUBLESHOOTING.md b/docs/TROUBLESHOOTING.md
index 1c5035cb1..f55fba05b 100644
--- a/docs/TROUBLESHOOTING.md
+++ b/docs/TROUBLESHOOTING.md
@@ -116,6 +116,40 @@ Check system logs for an out-of-memory kill. Also check `ulimit -R`: a desktop-s
kill even when memory is available. The engine prints a warning for that condition; see the
[detailed troubleshooting table](DETAILS.md#troubleshooting) before changing system limits.
+**Windows AMD: the driver resets (VIDEO_ENGINE_TIMEOUT_DETECTED / screen flicker / the engine dies mid-answer).**
+Windows gives a GPU about 2 seconds to answer; when a graphics card does not, it resets the driver (a TDR): the screen
+flickers, the engine dies, and the Event Viewer shows `VIDEO_ENGINE_TIMEOUT_DETECTED` (#613, with #579 and #541 on
+Linux). Strata 0.1.39 and newer say "the GPU stopped responding" in the log. It was seen with KV streaming on
+(`--kv-resident 32768`, which setup turns on from 64K context) while reading a long prompt on a gfx1201 card. Try these
+in order, one at a time, and tell us what changed:
+1. **Send us the evidence.** The last ~80 lines of the engine log (`strata-<model>.log` in the Strata folder of a source checkout; the server window
+ shows the same lines), your AMD driver version (AMD Software > System), your card and Windows version, the Strata
+ version, and the exact steps (context size, how long the prompt was, which app sent it). If Windows wrote a
+ dump, the newest `.dmp` in `C:\Windows\LiveKernelReports\WATCHDOG` (or `C:\Windows\Minidump`) helps; it holds no
+ chats, only the driver state.
+2. **Find the step that hangs:** add `"STRATA_PF_STEP_SYNC": "1"` to the `"env"` block of the model's run config (`strata-<model>.json`
+ in a source checkout) and restart. The prompt path then waits for the GPU after each step and logs any step over 250 ms, so the log names
+ the step. It is slower; use it to diagnose, then take it out.
+3. **`"STRATA_KV_HOST_DMA": "1"`** in the same `"env"` block: no GPU kernel writes the RAM copy of the K/V during a
+ prompt, it is copied by DMA instead. Same answers.
+4. **No KV streaming:** run setup again and pick 32K context (or remove `--kv-resident` and its number from
+ `"args"` in the JSON, with a context that fits the VRAM).
+5. **A smaller prompt chunk:** change `--prefill` in `"args"` (for example `--prefill 512`): each GPU launch then does
+ less work between two checks by Windows. Prompts are read more slowly.
+6. **Optional, your decision: give Windows more time (`TdrDelay`).** The default is 2 seconds. In the registry,
+ `HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\Control\GraphicsDrivers`, a DWORD `TdrDelay` of `10` (seconds)
+ lets a long GPU job finish before Windows resets the driver; restart the PC. It hides the symptom and does not fix
+ a GPU that has really hung, and a hung GPU then freezes the screen for those 10 seconds. Strata changes no Windows
+ setting itself; to undo it, delete the value.
+7. **Driver:** use the newest AMD Software release for your card (Adrenalin, not a Windows Update driver) and restart
+ after installing. If it started after a driver update, tell us both versions; going back one version is a fair
+ test.
+
+**Large pinned host allocations fail on ROCm although RAM is free.**
+See [AMD_HIP.md](AMD_HIP.md#model-and-serving-configuration): the mapped expert mode avoids the full pinned arena.
+
+**"verify: timed out at layer N" or "no progress for 60 s" on AMD (Linux), mostly with `--mmap-experts`.**
+
**A hand-edited engine option disappears.**
The run config tracks explicit options in `user_args` and the generated baseline in `args_written`. Prefer the
app's Expert settings or Terminal `--set` for supported overrides. Context, KV, picture reading and drafting are