From 7daf9896e5c09949f53218082110e3b34dc4dff3 Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Fri, 14 Aug 2026 03:49:42 -0700
Subject: [PATCH] docs: record Ling freeze diagnosis - spec path deadlock,
 resolution spec-off parallel=2

---
 docs/ling-3.0-flash-trial.md | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/docs/ling-3.0-flash-trial.md b/docs/ling-3.0-flash-trial.md
index ab85d64..254c74b 100644
--- a/docs/ling-3.0-flash-trial.md
+++ b/docs/ling-3.0-flash-trial.md
@@ -48,6 +48,31 @@ Vulkan0: AMD Radeon Graphics (RADV STRIX_HALO) (113910 MiB)
 Ling uses gated MLA and KDA attention. KV cache stays tiny: 256k total
 context costs only ~2.5 GiB. This is why 256k context fits.
 
+## Freeze Bug (2026-08-14) - Spec Path Deadlock
+
+### Symptom
+
+Under 2+ concurrent streams with speculative decoding, one stream hard-freezes
+mid-generation (zero output for minutes; a deadlock, not slowness). Freeze
+point varies (385-1588 tokens). Single streams never freeze.
+
+### Isolated cause
+
+- Not context exhaustion: `truncated = 0`, under 131072 ctx.
+- Not batch (3072 and 8192 both froze) and not log verbosity (0 and 4 both).
+- `parallel=2` + `draft-mtp,ngram-mod` -> freeze.  SPEC OFF -> no freeze.
+- Culprit: the speculative-decode / context-checkpoint path in llama-server
+  with multiple slots on the Vulkan backend. Known bug family: PR #24891,
+  #24797 (server checkpoint fixes), #25144 (MTP draft crash), plus a
+  ggml-vulkan hang-under-sustained-compute class.
+
+### Resolution: SPEC OFF
+
+`SPEC_TYPE=none`, `PARALLEL=2`.  All concurrent streams complete (EOS).
+Speed cost: ~10-13 t/s under contention vs ~28-32 t/s single-stream with
+MTP.  Fallback chain if spec-off regresses: A) `PARALLEL=1` keep MTP,
+B) switch back to Qwen3.6-27B (frank-default-large, MTP n_max 3).
+
 ## Files
 
 - `scripts/frank-large-ling.service` - systemd unit.