diff --git a/recipes/glm-5-3-flash-4x170hx-tp4-pp4-morrowmake-141/recipe.yaml b/recipes/glm-5-3-flash-4x170hx-tp4-pp4-morrowmake-141/recipe.yaml
index 9e9ec051c..35374c9b4 100644
--- a/recipes/glm-5-3-flash-4x170hx-tp4-pp4-morrowmake-141/recipe.yaml
+++ b/recipes/glm-5-3-flash-4x170hx-tp4-pp4-morrowmake-141/recipe.yaml
@@ -1,13 +1,14 @@
 slug: glm-5-3-flash-4x170hx-tp4-pp4-morrowmake-141
-title: 'GLM-5.3-Flash on 4x CMP 170HX — Morrowmake recipe 1.4.1, TP4 DFlash2'
+title: 'GLM-5.3-Flash on 4x CMP 170HX — Morrowmake recipe 1.7.2, TP4 DFlash2'
 engine:
   name: vllm
-  version: 'Morrowmake/vllm-cmp170hx @ 378c37b009'
+  version: 'Morrowmake/vllm-cmp170hx @ ab60b723ada'
   source_type: docker_image
-  image_digest: 'ghcr.io/morrowmake/vllm-cmp170hx@sha256:14d7b380cc623eb9145db06307c0e432024f1060de1460bf14f893abd9792a97'
+  image_digest: 'ghcr.io/morrowmake/vllm-cmp170hx@sha256:0d249835cb8502316403350a3cad9d531b46e5249e4076ecb70faa42067b5b7a'
+  image: 'ghcr.io/morrowmake/vllm-cmp170hx:1.7.2-ab60b723ad'
   git_url: 'https://github.com/Morrowmake/vllm-cmp170hx'
-  pinned_commit: 378c37b0098a41a5cd25b3bf8b56d158e33a6cbf
-summary: 'PP4 (pipeline-parallel 4, TP1) as-run on a 4x CMP 170HX rig 2026-09-28 at --gpu-memory-utilization 0.93 after 0.95 OOM-killed warmup (a 72 MiB KDA prefill workspace did not fit in the ~70 MiB left on the last card). Author 1.4.1 measurements below are TP4 unless labeled PP4; KV pool 2,320,328 tokens under PP4.'
+  pinned_commit: ab60b723ada254a442a4ba5ff27bf837aa27ef83
+summary: 'PP4 (pipeline-parallel 4, TP1) as-run on a 4x CMP 170HX rig 2026-09-28 at --gpu-memory-utilization 0.93 after 0.95 OOM-killed warmup (a 72 MiB KDA prefill workspace did not fit in the ~70 MiB left on the last card). Author 1.4.1 measurements below are TP4 unless labeled PP4; KV pool 2,320,328 tokens under PP4. Recipe release 1.7.2 2026-10-06 (engine ab60b723, image 1.7.2-ab60b723ad) — updated from 1.4.1; upstream fixes: TP4 long-gen state recovery (#7), prefill scratch OOM (#9), cached-prefix garbage output (#10), Marlin prefill dependency order (#4); measured tok/s on site unchanged (upstream validates speeds unchanged within noise).'
 model:
   name: GLM-5.3-Flash-W4A16-MTP
   family: glm
@@ -67,8 +68,8 @@ config:
     - '--max-num-partial-prefills'
     - '2'
   runtime:
-    container: 'docker run -d --name glm53-flash --user "$(id -u):$(id -g)" --workdir /cache --gpus all --shm-size 16g -p 127.0.0.1:8000:8000 --env-file docker/container.env -v serve.sh:/recipe/serve.sh:ro -v models/GLM-5.3-Flash-W4A16-MTP:/models/GLM-5.3-Flash-W4A16-MTP:ro -v models/GLM-5.3-Flash-DFlash2:/models/GLM-5.3-Flash-DFlash2:ro -v cache:/cache --entrypoint /bin/bash ghcr.io/morrowmake/vllm-cmp170hx@sha256:14d7b380cc623eb9145db06307c0e432024f1060de1460bf14f893abd9792a97 /recipe/serve.sh'
-    env: 'LAYOUT=tp4 (x16 links) or LAYOUT=pp4 (x4 links; 2312 max-num-batched-tokens). container.env: VLLM_ALLOW_PCIE_P2P_CUSTOM_ALLREUSE=0 (set 1 if nvidia-smi topo -p2p r says OK for every pair; worth +5% decode/+13.7% prefill under TP4). HF_HOME/FLASHINFER_WORKSPACE_BASE/TORCHINDUCTOR_CACHE_DIR under ./cache so first-boot FlashInfer compile (4-5 min) happens once.'
+    container: 'docker run -d --name glm53-flash --user "$(id -u):$(id -g)" --workdir /cache --gpus all --shm-size 16g -p 127.0.0.1:8000:8000 --env-file docker/container.env -v serve.sh:/recipe/serve.sh:ro -v models/GLM-5.3-Flash-W4A16-MTP:/models/GLM-5.3-Flash-W4A16-MTP:ro -v models/GLM-5.3-Flash-DFlash2:/models/GLM-5.3-Flash-DFlash2:ro -v cache:/cache --entrypoint /bin/bash ghcr.io/morrowmake/vllm-cmp170hx@sha256:0d249835cb8502316403350a3cad9d531b46e5249e4076ecb70faa42067b5b7a /recipe/serve.sh'
+    env: 'LAYOUT=tp4 (x16 links) or LAYOUT=pp4 (x4 links; 2312 max-num-batched-tokens). container.env: VLLM_ALLOW_PCIE_P2P_CUSTOM_ALLREDUCE=0 (set 1 if nvidia-smi topo -p2p r says OK for every pair; worth +5% decode/+13.7% prefill under TP4). HF_HOME/FLASHINFER_WORKSPACE_BASE/TORCHINDUCTOR_CACHE_DIR under ./cache so first-boot FlashInfer compile (4-5 min) happens once. Updated to Morrowmake release 1.7.2 2026-10-06: image pin 1.7.2-ab60b723ad, digest sha256:0d249835cb8502316403350a3cad9d531b46e5249e4076ecb70faa42067b5b7a. ./start.sh update preserves .env and adopts the 1.7.2 defaults (RecoverSSM on at TP4, adaptive DFlash2 depth on, BOOT_CHECK=1) unless set explicitly; upstream ignores the old VLLM_GLM5_MARLIN_PREFILL_CUDA switch (never set here).'
     notes: 'PP4 layout: activations-only inter-card traffic, tuned for x4-link cards, 2.34x faster prefill (6254 vs 2670), 2.01x KV pool. start.sh checks link width and suggests LAYOUT=pp4 automatically. The image runs at native-install speed (within 0.4%). All sm_80 feature flags are kill switches via env (VLLM_GLM5_PREFILL_KERNELS, VLLM_GLM5_DECODE_KERNELS, FAIR_PREFILL etc.).'
 performance:
   claimed_by: submitter
@@ -92,17 +93,17 @@ artifacts:
     kind: engine_image
     pointer_type: docker_digest
     pointer: 'https://github.com/Morrowmake/vllm-cmp170hx'
-    pin: 'image ghcr.io/morrowmake/vllm-cmp170hx (release 1.4.1; the 1.4.1 digest is no longer on GHCR and never had an unsuffixed tag. Public image tags: 1.3.0-0ed7d3e7f3, 1.5.0-e77f89da20, 1.6.0-3a2bf16dae. 1.5.0/1.6.0 serve.sh is launch-compatible with this 1.4.1 recipe (same dflash k=3 path); the perf numbers below are release-1.4.1. Or build 1.4.1 from github.com/Morrowmake/vllm-cmp170hx)'
+    pin: 'image ghcr.io/morrowmake/vllm-cmp170hx:1.7.2-ab60b723ad, digest sha256:0d249835cb8502316403350a3cad9d531b46e5249e4076ecb70faa42067b5b7a (recipe release 1.7.2). Public image tags: 1.7.2-ab60b723ad, 1.6.0-3a2bf16dae, 1.5.0-e77f89da20. The 1.7.2 serve.sh is launch-compatible with this as-run PP4 config (same dflash k=3 path); the perf numbers below remain release-1.4.1 measurements (1.7.2 validates speeds unchanged within noise).'
   -
     kind: reference
     pointer_type: git_commit
     pointer: 'https://github.com/Morrowmake/glm53-flash-cmp170hx-recipe'
-    pin: 'release 1.4.1 (engine source; image tags on GHCR: 1.3.0-0ed7d3e7f3, 1.5.0-e77f89da20, 1.6.0-3a2bf16dae)'
+    pin: 'release 1.7.2 (engine source; image tags on GHCR: 1.7.2-ab60b723ad, 1.6.0-3a2bf16dae, 1.5.0-e77f89da20)'
 provenance:
   source_urls:
     - 'https://github.com/Morrowmake/vllm-cmp170hx/tree/ampere-glm53'
     - 'https://huggingface.co/zai-org/GLM-5.3-Flash'
-  notes: 'Recipe by Morrowmake (github.com/Morrowmake/glm53-flash-cmp170hx-recipe, MIT licence), release 1.4.1 2026-09-27. Mirrored into localairecipes from the local checkout with every pin transcribed verbatim; engine+image+weights are digest/commit-pinned so this exact stack is reproducible.'
+  notes: 'Recipe by Morrowmake (github.com/Morrowmake/glm53-flash-cmp170hx-recipe, MIT licence), release 1.4.1 2026-09-27. Mirrored into localairecipes from the local checkout with every pin transcribed verbatim; engine+image+weights are digest/commit-pinned so this exact stack is reproducible. Updated 2026-10-06 from upstream release 1.4.1 to 1.7.2 (engine ab60b723ada, image 1.7.2-ab60b723ad): TP4 long-gen state recovery (#7), prefill scratch OOM (#9), cached-prefix garbage output (#10), Marlin prefill dependency order (#4), startup retry for slow warmup (#5); as-run launch args unchanged (still the 1.7.2 PP4 defaults); measured tok/s on site unchanged (upstream validates speeds unchanged within noise).'
   credit:
     -
       name: Morrowmake