mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-07-30 09:57:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

chore: ⬆️ Update antirez/ds4 to efdadd41e20134af4f3381e1ed90e96fe4faef6f (#11010)

Browse Source 
* ⬆️ Update antirez/ds4

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

* fix(ds4): link new tensor parallel objects

The updated ds4 revision split tensor-parallel transport and layer placement into separate translation units. Build and link those objects on CPU, CUDA, and Metal builds.

Assisted-by: Codex:gpt-5

---------

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:
mudler's LocalAI [bot]
2026-07-21 18:06:30 +02:00
committed by GitHub
parent 4ce67ccb84
commit 3584e0776d
2 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
backend/cpp/ds4/CMakeLists.txt
View File

@@ -76,12 +76,13 @@ elseif(DS4_GPU STREQUAL "cpu")
set(DS4_OBJS "${DS4_DIR}/ds4_cpu.o")
endif()
# ds4.c now references ds4_distributed.c (distributed inference) and ds4_ssd.c
# (SSD expert-cache), each split into its own translation unit upstream. Both
# are GPU-agnostic objects shared by every GPU mode, so link them in regardless
# of DS4_GPU.
# Upstream splits distributed inference, tensor-parallel transport, the SSD
# expert cache, and layer placement into GPU-agnostic translation units. Link
# them regardless of DS4_GPU.
list(APPEND DS4_OBJS "${DS4_DIR}/ds4_distributed.o")
list(APPEND DS4_OBJS "${DS4_DIR}/ds4_tp.o")
list(APPEND DS4_OBJS "${DS4_DIR}/ds4_ssd.o")
list(APPEND DS4_OBJS "${DS4_DIR}/ds4_layer_pack.o")
add_executable(${TARGET}
grpc-server.cpp

23
backend/cpp/ds4/Makefile
View File

@@ -1,10 +1,10 @@
# ds4 backend Makefile.
#
# Upstream pin lives below as DS4_VERSION?=80ebbc396aee40eedc1d829222f3362d10fa4c6c
# Upstream pin lives below as DS4_VERSION?=efdadd41e20134af4f3381e1ed90e96fe4faef6f
# (.github/bump_deps.sh) can find and update it - matches the
# llama-cpp / ik-llama-cpp / turboquant convention.
DS4_VERSION?=80ebbc396aee40eedc1d829222f3362d10fa4c6c
DS4_VERSION?=efdadd41e20134af4f3381e1ed90e96fe4faef6f
DS4_REPO?=https://github.com/antirez/ds4
CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
@@ -18,20 +18,19 @@ UNAME_S := $(shell uname -s)
CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release
# ds4_distributed.o and ds4_ssd.o are GPU-agnostic translation units that
# ds4.c/ds4_cpu.o now reference (upstream split distributed inference and the
# SSD expert-cache into their own .c files). Both objects are shared by every
# GPU mode, so they are appended unconditionally below.
# Upstream splits distributed inference, tensor-parallel transport, the SSD
# expert cache, and layer placement into GPU-agnostic translation units. They
# are shared by every GPU mode, so append them unconditionally below.
ifeq ($(BUILD_TYPE),cublas)
CMAKE_ARGS += -DDS4_GPU=cuda
DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o ds4_ssd.o
DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
else ifeq ($(UNAME_S),Darwin)
CMAKE_ARGS += -DDS4_GPU=metal
DS4_OBJ_TARGET := ds4.o ds4_metal.o ds4_distributed.o ds4_ssd.o
DS4_OBJ_TARGET := ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
else
# CPU reference path (Linux only - macOS CPU path is broken by VM bug per ds4 README).
CMAKE_ARGS += -DDS4_GPU=cpu
DS4_OBJ_TARGET := ds4_cpu.o ds4_distributed.o ds4_ssd.o
DS4_OBJ_TARGET := ds4_cpu.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
endif
ifneq ($(NATIVE),true)
@@ -56,11 +55,11 @@ 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_ssd.o
+$(MAKE) -C ds4 ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
else ifeq ($(UNAME_S),Darwin)
+$(MAKE) -C ds4 ds4.o ds4_metal.o ds4_distributed.o ds4_ssd.o
+$(MAKE) -C ds4 ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
else
+$(MAKE) -C ds4 ds4_cpu.o ds4_distributed.o ds4_ssd.o
+$(MAKE) -C ds4 ds4_cpu.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
endif
grpc-server: ds4/ds4.o