From 52ae025135ec3ed62cf7e30f97bfc4c19f253418 Mon Sep 17 00:00:00 2001 From: bcloud Date: Sat, 14 Nov 2026 23:10:32 -0400 Subject: [PATCH] third_party/llama.cpp: pin to aae78ecdf -- carry the fast-greedy observable the engine currently lacks Main pins 669178cb0, one commit behind the fork head. The missing commit is #391: aae78ecdf common/sampling: log whether the fast greedy path was taken, so eligibility drift is observable (#391) 669178cb0 hrx: one-token GDN decode updates the recurrent state in place (no 12.6 MB state copy per token) (#390) 6d6cb0f32 hrx: strict refuses a misplacement, not a placement the code calls by design (#389) Why this one commit matters beyond being current: #391 exists to be READ from a served binary's log. engine#2452's review asked for an engine-level greedy comparison and it cannot be written while the engine has no observable -- `git show 669178cb0:common/sampling.cpp | grep -c LLAMA_LOG_FAST_GREEDY` = 0 -- so the arm stays owed for a reason that is one line away from disappearing. Verified at this pin (engine build, submodule checked out at aae78ecd and the sha printed by the build): BUILD_RC=0 0 real compile errors 3 objects recompiled (llama-graph / sampling / relink) /hrx/llama/bin/llama-server relinked registry: regenerated for the new pin, --check-pins rc 0. Not claimed: the engine-level fast-greedy arm itself. It becomes writable with this pin and is still owed on the next device-or-CPU serve; what this PR removes is the reason it could not be written at all. --- registry/architectures.json | 2 +- third_party/llama.cpp | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/registry/architectures.json b/registry/architectures.json index f6ad38271..32ddd0b47 100644 --- a/registry/architectures.json +++ b/registry/architectures.json @@ -1,7 +1,7 @@ { "about": "HF architecture -> GGUF architecture and the backends whose code accepts it. Generated by tools/registry_build.py from the pinned sources; do not edit.", "sources": { - "llama.cpp (hrx)": "669178cb0a2fae7e3fbdf8d0a49c32aaf414f5dd" + "llama.cpp (hrx)": "aae78ecdf077a5f008ca81cc0de38b84e77ad5fe" }, "counts": { "hrx": 350, diff --git a/third_party/llama.cpp b/third_party/llama.cpp index 669178cb0..aae78ecdf 160000 --- a/third_party/llama.cpp +++ b/third_party/llama.cpp @@ -1 +1 @@ -Subproject commit 669178cb0a2fae7e3fbdf8d0a49c32aaf414f5dd +Subproject commit aae78ecdf077a5f008ca81cc0de38b84e77ad5fe