From 5837b1488805fdc6310d92a2842993b9abc736b4 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 17 Apr 2026 08:12:21 +0200 Subject: [PATCH] chore: :arrow_up: Update TheTom/llama-cpp-turboquant to `45f8a066ed5f5bb38c695cec532f6cef9f4efa9d' (#9385) chore: :arrow_up: Update TheTom/llama-cpp-turboquant to `45f8a066ed5f5bb38c695cec532f6cef9f4efa9d` Drop 0002-ggml-rpc-bump-op-count-to-97.patch; the fork now has GGML_OP_COUNT == 97 and RPC_PROTO_PATCH_VERSION 2 upstream. Fetch all tags in backend/cpp/llama-cpp/Makefile so tag-only commits (the new turboquant pin is reachable only through the tag feature-turboquant-kv-cache-b8821-45f8a06) can be checked out. --- backend/cpp/llama-cpp/Makefile | 2 +- backend/cpp/turboquant/Makefile | 2 +- .../patches/0002-ggml-rpc-bump-op-count-to-97.patch | 13 ------------- 3 files changed, 2 insertions(+), 15 deletions(-) delete mode 100644 backend/cpp/turboquant/patches/0002-ggml-rpc-bump-op-count-to-97.patch diff --git a/backend/cpp/llama-cpp/Makefile b/backend/cpp/llama-cpp/Makefile index 3f45e85e7..8157ce0bb 100644 --- a/backend/cpp/llama-cpp/Makefile +++ b/backend/cpp/llama-cpp/Makefile @@ -132,7 +132,7 @@ llama.cpp: cd llama.cpp && \ git init && \ git remote add origin $(LLAMA_REPO) && \ - git fetch origin && \ + git fetch --all --tags && \ git checkout -b build $(LLAMA_VERSION) && \ git submodule update --init --recursive --depth 1 --single-branch diff --git a/backend/cpp/turboquant/Makefile b/backend/cpp/turboquant/Makefile index 624e63d17..7d0abf0e2 100644 --- a/backend/cpp/turboquant/Makefile +++ b/backend/cpp/turboquant/Makefile @@ -1,7 +1,7 @@ # Pinned to the HEAD of feature/turboquant-kv-cache on https://github.com/TheTom/llama-cpp-turboquant. # Auto-bumped nightly by .github/workflows/bump_deps.yaml. -TURBOQUANT_VERSION?=8590cbff961dbaf1d3a9793fd11d402e248869b9 +TURBOQUANT_VERSION?=45f8a066ed5f5bb38c695cec532f6cef9f4efa9d LLAMA_REPO?=https://github.com/TheTom/llama-cpp-turboquant CMAKE_ARGS?= diff --git a/backend/cpp/turboquant/patches/0002-ggml-rpc-bump-op-count-to-97.patch b/backend/cpp/turboquant/patches/0002-ggml-rpc-bump-op-count-to-97.patch deleted file mode 100644 index 19bf07c59..000000000 --- a/backend/cpp/turboquant/patches/0002-ggml-rpc-bump-op-count-to-97.patch +++ /dev/null @@ -1,13 +0,0 @@ -diff --git a/ggml/include/ggml-rpc.h b/ggml/include/ggml-rpc.h -index 1c11495..31af239 100644 ---- a/ggml/include/ggml-rpc.h -+++ b/ggml/include/ggml-rpc.h -@@ -11,7 +11,7 @@ extern "C" { - #define RPC_PROTO_PATCH_VERSION 1 - - #ifdef __cplusplus --static_assert(GGML_OP_COUNT == 96, "GGML_OP_COUNT has changed - update RPC_PROTO_PATCH_VERSION"); -+static_assert(GGML_OP_COUNT == 97, "GGML_OP_COUNT has changed - update RPC_PROTO_PATCH_VERSION"); - #endif - - #define GGML_RPC_MAX_SERVERS 16