diff --git a/recipes/glm-5-3-flash-exlr8-exl3-experts-on-dgx-spark-tp1-4/recipe.yaml b/recipes/glm-5-3-flash-exlr8-exl3-experts-on-dgx-spark-tp1-4/recipe.yaml
index ab0f4d024..79db03010 100644
--- a/recipes/glm-5-3-flash-exlr8-exl3-experts-on-dgx-spark-tp1-4/recipe.yaml
+++ b/recipes/glm-5-3-flash-exlr8-exl3-experts-on-dgx-spark-tp1-4/recipe.yaml
@@ -4,9 +4,9 @@ engine:
   name: vllm
   version: vllm-exlr8@a2e163cb05
   source_type: fork
-  git_url: 'https://github.com/kindlingai/vllm-exlr8'
+  git_url: 'https://github.com/kindlingai/glm-5.3-flash-exlr8-gx10'
   pinned_commit: a2e163cb05
-  install_note: 'Source build: docker build -f image/Dockerfile . The overlay sets --quantization exlr8 --load-format exlr8 over the NVFP4 Flash base image.'
+  install_note: 'Source build: docker build -f image/Dockerfile . The overlay sets --quantization exlr8 --load-format exlr8 over the NVFP4 Flash base image. The vllm engine tree arrives via the repo symlink vllm -> .submodules/spark-agent/vllm (submodule mmastrac/spark-agent); the fork revision a2e163cb05 is no longer resolvable in any public repo.'
 summary: 'GLM-5.3-Flash exlr8: MoE layers are EXL3-trellis units decoded by the custom exlr8 MoE kernel; dense linears stay FP8/NVFP4. One release carries three expert widths (k2/k3/k4 = 2/3/4 bpw), chosen at boot via VLLM_EXLR8_WIDTHS. Reference topology TP=4 on four GB10 boxes; TP=1 serves the whole model (~87 GiB) on one 128 GB DGX Spark / ASUS GX10 via tp1.yaml plus a distinct MENTAT_GROUP. TP=2 and TP=3 also measured. 2026-10-19, clocks TP-locked at 2200 MHz: decode code 128.0 tok/s, prose 72.5 at TP=4; 53.0 / 29.5 at TP=1; prefill 4,393 tok/s at 8K, 4,190 at 32K. Trade vs the shipping NVFP4 build: decode +3-8%, NLL equal or better, KV pool ~+15%, prefill 7.7% lower at Second 1x-Spark GLM-5.3-Flash lane: not the VQ Q4_K GGUF lane (/r/glm-5-3-flash-vq-q4-k-1x-dgx-spark-1m-ctx-jlfn), and not a fork of the 2x ATLAS build (/r/glm-5-3-flash-nvfp4-on-2x-dgx-spark-atlas-rc4-2-tp2-dflash2-1m) whose NVFP4 Flash base this stack overlays.'
 license: MIT
 model:
@@ -137,7 +137,7 @@ artifacts:
   -
     kind: reference
     pointer_type: git_commit
-    pointer: 'https://github.com/mmastrac/glm-5.3-flash-4x-gx10'
+    pointer: 'https://github.com/kindlingai/glm-5.3-flash-gx10'
     pin: mmastrac/glm-5.3-flash-4x-gx10@0d1f462
 provenance:
   credit:
@@ -149,6 +149,6 @@ provenance:
       url: 'https://huggingface.co/nvidia/GLM-5.3-Flash-NVFP4'
   source_urls:
     - 'https://github.com/kindlingai/glm-5.3-flash-exlr8-gx10'
-    - 'https://github.com/mmastrac/glm-5.3-flash-4x-gx10'
+    - 'https://github.com/kindlingai/glm-5.3-flash-gx10'
     - 'https://huggingface.co/kindlingai/glm-5.3-flash-exlr8-k2-k3-k4'
   notes: "Upstream pinned at main @ 6f5ede7f2d2675fadbb9bb216a34b28386547c27 (re-read live 2026-10-23). Figures from README.md (author campaign 2026-10-19, clocks TP-locked at 2200 MHz); stack and knob detail from NOTES.md, KNOBS.md, experimental/compose/exlr8.yaml and tp1.yaml at that sha. corrections_to_card: (1) card called this the first single-DGX-Spark GLM-5.3-Flash recipe; that is wrong -- glm-5-3-flash-vq-q4-k-1x-dgx-spark-1m-ctx-jlfn already carries a 1x Spark lane, so this is a SECOND single-box lane on a different weight path (EXL3-trellis experts vs the VQ Q4_K GGUF lane); cross-linked to that recipe and to glm-5-3-flash-nvfp4-on-2x-dgx-spark-atlas-rc4-2-tp2-dflash2-1m. (2) the card's perf table put 2,609 in the TP=2 decode-prose column; README gives 2,609 as TP=2 cold prefill at 8K and 50.1 tok/s for TP=2 decode prose. (3) card asserted MIT for the recipe repo; GitHub reports no license for it and there is no LICENSE file at the pinned sha -- MIT is asserted here for the redistributed expert units and the base NVFP4 weights, not the recipe repo. (4) no upstream release tag exists; the reference is the pinned commit."