chore: ⬆️ Update antirez/ds4 to b7e9f0091139999b6c070a57590c447c5741da5c (#11333)

* ⬆️ Update antirez/ds4

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* fix(ds4): link upstream CUDA MMQ objects

The updated ds4 CUDA object now calls into the vendored MMQ implementation. Build and link those objects into both the gRPC server and distributed worker.

Assisted-by: Codex:gpt-5 [Codex]

---------

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
This commit is contained in:
authored and GitHub committed 2026-08-04 15:27:03 +02:00
1 parent 750ab91b2b
commit 137dfcf15a
2 files changed
+15 -5

No files matched your search

+9 -1
View File
@@ -69,7 +69,15 @@ target_include_directories(hw_grpc_proto PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
set(DS4_OBJS "${DS4_DIR}/ds4.o")
if(DS4_GPU STREQUAL "cuda")
list(APPEND DS4_OBJS "${DS4_DIR}/ds4_cuda.o")
list(APPEND DS4_OBJS
"${DS4_DIR}/ds4_cuda.o"
"${DS4_DIR}/cuda/mmq/ds4_ggml_stubs.o"
"${DS4_DIR}/cuda/mmq/ds4_mmq.o"
"${DS4_DIR}/cuda/mmq/ds4_mmq_d2r.o"
"${DS4_DIR}/cuda/mmq/quantize.o"
"${DS4_DIR}/cuda/mmq/mmid.o"
"${DS4_DIR}/cuda/mmq/mmvq.o"
"${DS4_DIR}/cuda/mmq/ds4_repack.o")
elseif(DS4_GPU STREQUAL "metal")
list(APPEND DS4_OBJS "${DS4_DIR}/ds4_metal.o")
elseif(DS4_GPU STREQUAL "cpu")
+6 -4
View File
@@ -1,10 +1,10 @@
# ds4 backend Makefile.
#
# Upstream pin lives below as DS4_VERSION?=54b36ed9ba42da31b24f2d1a5feb075c2475dbb1
# Upstream pin lives below as DS4_VERSION?=b7e9f0091139999b6c070a57590c447c5741da5c
# (.github/bump_deps.sh) can find and update it - matches the
# llama-cpp / ik-llama-cpp / turboquant convention.
DS4_VERSION?=54b36ed9ba42da31b24f2d1a5feb075c2475dbb1
DS4_VERSION?=b7e9f0091139999b6c070a57590c447c5741da5c
DS4_REPO?=https://github.com/antirez/ds4
CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
@@ -23,7 +23,9 @@ CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release
# are shared by every GPU mode, so append them unconditionally below.
ifeq ($(BUILD_TYPE),cublas)
CMAKE_ARGS += -DDS4_GPU=cuda
DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o \
cuda/mmq/ds4_ggml_stubs.o cuda/mmq/ds4_mmq.o cuda/mmq/ds4_mmq_d2r.o \
cuda/mmq/quantize.o cuda/mmq/mmid.o cuda/mmq/mmvq.o cuda/mmq/ds4_repack.o
else ifeq ($(UNAME_S),Darwin)
CMAKE_ARGS += -DDS4_GPU=metal
DS4_OBJ_TARGET := ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
@@ -55,7 +57,7 @@ ds4:
# the right per-platform compile flags (Objective-C/Metal on Darwin, nvcc on Linux+CUDA).
ds4/ds4.o: ds4
ifeq ($(BUILD_TYPE),cublas)
+$(MAKE) -C ds4 ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
+$(MAKE) -C ds4 $(DS4_OBJ_TARGET)
else ifeq ($(UNAME_S),Darwin)
+$(MAKE) -C ds4 ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
else