From b3cfdfac4a92344615f660a5b6054d540af1fef8 Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Tue, 30 Jun 2026 15:54:23 +0000
Subject: [PATCH] docs(paged): record GB10 parity source provenance

Add the clean llama.cpp fork state, base merge point, patch count, and tree-match result for the Phase 0 parity reopen workflow.

Assisted-by: Codex:gpt-5
---
 .../docs/GB10_PARITY_PHASE0_RESULTS.md             | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/backend/cpp/llama-cpp-localai-paged/docs/GB10_PARITY_PHASE0_RESULTS.md b/backend/cpp/llama-cpp-localai-paged/docs/GB10_PARITY_PHASE0_RESULTS.md
index 3585d7444..2ab55514d 100644
--- a/backend/cpp/llama-cpp-localai-paged/docs/GB10_PARITY_PHASE0_RESULTS.md
+++ b/backend/cpp/llama-cpp-localai-paged/docs/GB10_PARITY_PHASE0_RESULTS.md
@@ -16,8 +16,20 @@ Status: in progress.
 
 No baseline runs have been started yet.
 
+## Source Provenance
+
+- Local llama.cpp fork: `/home/mudler/_git/llama.cpp`
+- Branch: `localai-paged`
+- Working tree: clean
+- HEAD: `51168c5eee2e35348d9006f0b2fab3dc6e7c01cc`
+- Base pin: `0ed235ea2c17a19fc8238668653946721ed136fd`
+- Merge-base with base pin: `0ed235ea2c17a19fc8238668653946721ed136fd`
+- LocalAI patch count: `38`
+- LocalAI patch mirror: applies cleanly to the base pin and tree-matches fork
+  HEAD.
+- Tree hash after patch application: `a73d759350277532a14e853e1fe78f08bbb74ce8`
+
 ## Open Items
 
-- Capture clean source provenance.
 - Reproduce paged prefill and decode baselines.
 - Find or recreate vLLM graph-node-traced difference-method decode artifacts.