docs: record DSpark single-slot switch + ROCm parallel crash (2026-08-15) across KB; refs AGENTS/deployment/benchmark/matrix/index

docs/qwen3.8-spec-matrix.md

@@ -4,7 +4,18 @@ This page records the speculative-decoding benchmark and the production
 tuning for the unsloth Qwen3.8-27B `UD-Q8_K_XL` service on Dankclaw
 (`frank-default-large`).
 
-## Result (applied)
+## Result (applied, 2026-08-15: DSpark)
+
+- Model: `Qwen3.8-27B-UD-Q8_K_XL.gguf` (29.29 GiB, bundled MTP).
+- Spec: **DSpark sidecar draft** `magnitudedev/Qwen3.8-27B-DSpark-GGUF`
+  (`Qwen3.8-27B-DSpark-Q8_0.gguf`, 1.36B, block_size 7), `--spec-type
+  draft-dspark`, `--spec-draft-n-max 7` (clamps to block_size).
+- **PARALLEL=1.**  Two concurrent 16k prose prompts crashed the ROCm backend
+  with `ROCm error: an illegal memory access` during per-sequence block
+  sampling.  See the DSpark parallel incident below.
+- Batch 8192 / ubatch 256, ctx 524288 (262144 per slot).
+
+## Result (superseded 2026-08-14: bundled MTP)
 
 - Model: `Qwen3.8-27B-UD-Q8_K_XL.gguf` (29.29 GiB, bundled MTP).
 - Spec: `draft-mtp`, `--spec-draft-n-max 5`, no `--spec-draft-p-min`.
@@ -12,6 +23,51 @@ tuning for the unsloth Qwen3.8-27B `UD-Q8_K_XL` service on Dankclaw
 - Realistic-prompt generation: ~13.3 t/s single, ~8 t/s per slot under
   2 concurrent streams. No premature stop.
 
+## Incident: DSpark ROCm Crash Under Parallel Load (2026-08-15)
+
+A two-stream parallel acceptance test crashed `frank-default-large`.
+
+```mermaid
+graph TD
+    A[Two concurrent 16k prose prompts<br>high prompt-cache reuse] --> B[ROCm illegal memory access<br>in common_speculative_impl_draft_dflash::draft]
+    B --> C[status 6/ABRT core dump]
+    C --> D[systemd auto-restart, 503 during reload]
+    D --> E[pinned PARALLEL=1]
+```
+
+Trigger: two distinct-but-overlapping ~16k-token realistic prose prompts
+started simultaneously on PARALLEL=2.  The ROCm backend aborted at
+`ggml-cuda.cu:106` with `ROCm error: an illegal memory access was
+encountered`, surfacing in `hipStreamSynchronize` inside
+`common_speculative_impl_draft_dflash::draft` (the class used by
+`draft-dspark`).  `systemd` caught it (status 6/ABRT) and restarted the
+unit; in-flight streams saw `Remote end closed connection without response`
+until the ~reload finished.
+
+Mechanism: DSpark reuses the DFlash block-diffusion draft machinery.  The
+DFlash draft model uses one shared draft context (`ctx_dft`) across all
+parallel slots; under concurrent block drafting on ROCm it performs an
+illegal memory access (HIP stream sync).  This is the same multi-slot
+class of bug that retired `draft-dflash` for premature EOS; here it is a
+hard ROCm crash instead of a bad sample.
+
+Fix: pin **PARALLEL=1** (single slot).  With one slot, concurrent requests
+queue safely and each completes to `max_tokens`.  Revisit after an upstream
+multi-slot DSpark fix (DSpark is known-good single-slot).  Single-slot 16k
+prose generation was ~steady (measuring only the correct-size signal, not
+this page).
+
+## Parallel results by stream count (2026-08-15, correct-size tests)
+
+| Parallel | Two 16k prose prompts | Two 67k prose prompts |
+| -------- | -------------------- | --------------------- |
+| 2 | crashes (illegal mem access) | passes |
+| 1 | queues, both complete | n/a |
+
+Note: the crash manifests on the smaller (16k) concurrent streams, not the
+larger 67k pair.  Size is not the trigger; concurrent block drafting on the
+shared draft context is.
+
 ## How MTP works on Qwen3.8
 
 The unsloth `UD-*` GGUFs keep the MTP (Multi-Token Prediction) head inside
@@ -67,17 +123,19 @@ Two failure patterns appeared during early production tests:
 `scripts/frank-default-large.env`:
 
 ```ini
-SPEC_TYPE=draft-mtp
-SPEC_DRAFT_N_MAX=5
+SPEC_TYPE=draft-dspark
+DRAFT_FILE=Qwen3.8-27B-DSpark-Q8_0.gguf
+SPEC_DRAFT_N_MAX=7
 SPEC_DRAFT_P_MIN=
 BATCH_SIZE=8192
 UBATCH_SIZE=256
 CTX_SIZE=524288
-PARALLEL=2
+PARALLEL=1   # DSpark multi-slot crashes on this box (2026-08-15)
 ```
 
-Window: 524288 total / 2 = 262144 per slot, matching the pi
-`models.json` contextWindow for `frank-default-large`.
+Window: computed at 262144 per slot (the pi `models.json` contextWindow for
+`frank-default-large`).  The unit reports `n_ctx_slot = 262144`; CTX_SIZE is
+a pool ceiling and per-slot stays 262144 regardless of the single slot.
 
 ## See Also