From c4461e4fe3e71f434e44e8cb7c75fc1f35e88532 Mon Sep 17 00:00:00 2001 From: bong-water-water-bong Date: Sun, 15 Nov 2026 06:42:47 -0400 Subject: [PATCH] third_party/llama.cpp: pin to 8aa770fbd -- a DFlash draft no longer aborts llama-server's memory fit (llama.cpp#397) 6b9fcacb7 -> 8aa770fbd: llama.cpp#394 (tests for #393's loader hunk), #395 (the placement report names BY DESIGN off-HRX nodes, engine#2450), #396 (a buffer type must have an identity, engine#2500) and #397. #397: `1bit serve --dflash` on Qwen3.8-27B + DFlash2 q8_0 aborted at load in the memory-fit probe (GGML_ASSERT ctx_other, src/models/dflash.cpp:944). The draft context now fails to create there and the fitter fits the target alone. Co-Authored-By: Claude Opus 5.5 --- 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 26ef53ff0..22b70d263 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)": "6b9fcacb7fbdff749060f25393577b8d7a5af5bc" + "llama.cpp (hrx)": "8aa770fbd94a8028b8b4a2c677a7aef9409778f4" }, "counts": { "hrx": 350, diff --git a/third_party/llama.cpp b/third_party/llama.cpp index 6b9fcacb7..8aa770fbd 160000 --- a/third_party/llama.cpp +++ b/third_party/llama.cpp @@ -1 +1 @@ -Subproject commit 6b9fcacb7fbdff749060f25393577b8d7a5af5bc +Subproject commit 8aa770fbd94a8028b8b4a2c677a7aef9409778f4