Skip to content

fix(turboquant,bonsai): do not apply vendored llama.cpp patches to fork trees #10866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mudler merged 1 commit into from
Jul 16, 2026
+22 −4
Merged

fix(turboquant,bonsai): do not apply vendored llama.cpp patches to fork trees #10866

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions backend/cpp/bonsai/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,10 @@ PATCHES_DIR := $(CURRENT_MAKEFILE_DIR)/patches
define bonsai-build
rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build
cp -rf $(LLAMA_CPP_DIR) $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build
# Drop patches vendored for upstream llama.cpp: the fork tree diverges, so
# they reject there. Fork-specific patches live in backend/cpp/bonsai/patches/
# and are applied by apply-patches.sh below.
rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build/patches
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-$(1)-build purge
$(info $(GREEN)I bonsai build info:$(1)$(RESET))
LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(BONSAI_VERSION) \
Expand Down Expand Up @@ -68,6 +72,10 @@ bonsai-fallback:
bonsai-cpu-all:
rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build
cp -rf $(LLAMA_CPP_DIR) $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build
# Drop patches vendored for upstream llama.cpp: the fork tree diverges, so
# they reject there. Fork-specific patches live in backend/cpp/bonsai/patches/
# and are applied by apply-patches.sh below.
rm -rf $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build/patches
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../bonsai-cpu-all-build purge
$(info $(GREEN)I bonsai build info:cpu-all-variants$(RESET))
LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(BONSAI_VERSION) \
Expand Down
10 changes: 6 additions & 4 deletions backend/cpp/llama-cpp/prepare.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,19 @@
#!/bin/bash

set -e

## Patches

## Apply patches from the `patches` directory
## Apply patches from the `patches` directory. Runs under set -e so a
## rejected patch aborts the build here, loudly, instead of surfacing later
## as a confusing compile error. A missing or empty patches dir is a no-op.
if [ -d "patches" ]; then
for patch in $(ls patches); do
echo "Applying patch $patch"
patch -d llama.cpp/ -p1 < patches/$patch
done
done
fi

set -e

for file in $(ls llama.cpp/tools/server/); do
cp -rfv llama.cpp/tools/server/$file llama.cpp/tools/grpc-server/
done
Expand Down
8 changes: 8 additions & 0 deletions backend/cpp/turboquant/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,10 @@ PATCHES_DIR := $(CURRENT_MAKEFILE_DIR)/patches
define turboquant-build
rm -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-$(1)-build
cp -rf $(LLAMA_CPP_DIR) $(CURRENT_MAKEFILE_DIR)/../turboquant-$(1)-build
# Drop patches vendored for upstream llama.cpp: the fork tree diverges, so
# they reject there. Fork-specific patches live in backend/cpp/turboquant/patches/
# and are applied by apply-patches.sh below.
rm -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-$(1)-build/patches
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-$(1)-build purge
# Augment the copied grpc-server.cpp's KV-cache allow-list with the
# fork's turbo2/turbo3/turbo4 types. We patch the *copy*, never the
Expand Down Expand Up @@ -74,6 +78,10 @@ turboquant-fallback:
turboquant-cpu-all:
rm -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build
cp -rf $(LLAMA_CPP_DIR) $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build
# Drop patches vendored for upstream llama.cpp: the fork tree diverges, so
# they reject there. Fork-specific patches live in backend/cpp/turboquant/patches/
# and are applied by apply-patches.sh below.
rm -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/patches
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build purge
bash $(CURRENT_MAKEFILE_DIR)/patch-grpc-server.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/grpc-server.cpp
$(info $(GREEN)I turboquant build info:cpu-all-variants$(RESET))
Expand Down
Loading