danielkrause/colibri-strix
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Tiered CUDA acceleration for routed experts (opt-in, CPU default untouched) + REPLAY fixture harness (#16)

Browse Source 
* feat: add experimental CUDA backend for resident tensors

* feat: promote pinned experts to a bounded VRAM tier

* feat: preload the GPU expert tier at startup

* fix: harden CUDA backend failure handling

* feat: add deterministic multi-GPU tensor placement

* test: add deterministic CUDA benchmark fixture

* perf: make routed experts the default CUDA path
This commit is contained in:
ZacharyZcR
2026-07-10 13:41:09 +08:00
committed by GitHub
parent 4ea9ddc0f0
commit 57706a0200
9 changed files with 878 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/Makefile
+29 -3
View File
@@ -28,10 +28,36 @@ CFLAGS = -O3 -march=$(ARCH) -fopenmp -Wall -Wextra -Wno-unused-parameter -Wno-m
LDFLAGS = -lm -fopenmp
endif
# CUDA=1 adds an opt-in backend for resident tensors. The default build remains
# pure C and keeps the original zero-dependency runtime.
CUDA ?= 0
CUDA_HOME ?= /usr/local/cuda
NVCC ?= $(CUDA_HOME)/bin/nvcc
CUDA_ARCH ?= native
NVCCFLAGS ?= -O3 -std=c++17 -arch=$(CUDA_ARCH) -Xcompiler=-Wall,-Wextra
CUDA_OBJ =
ifeq ($(CUDA),1)
ifeq ($(UNAME_S),Darwin)
$(error CUDA=1 is supported only on Linux)
endif
CFLAGS += -DCOLI_CUDA
LDFLAGS += -L$(CUDA_HOME)/lib64 -Wl,-rpath,$(CUDA_HOME)/lib64 -lcudart -lstdc++
CUDA_OBJ = backend_cuda.o
endif
all: glm
glm: glm.c st.h json.h tok.h tok_unicode.h compat.h
$(CC) $(CFLAGS) glm.c -o glm $(LDFLAGS)
glm: glm.c st.h json.h tok.h tok_unicode.h compat.h $(CUDA_OBJ)
$(CC) $(CFLAGS) glm.c $(CUDA_OBJ) -o glm $(LDFLAGS)
backend_cuda.o: backend_cuda.cu backend_cuda.h
@command -v $(NVCC) >/dev/null 2>&1 || { echo "nvcc not found: set CUDA_HOME or NVCC" >&2; exit 1; }
$(NVCC) $(NVCCFLAGS) -c backend_cuda.cu -o $@
cuda-test: backend_cuda.cu backend_cuda.h backend_cuda_test.cu
@command -v $(NVCC) >/dev/null 2>&1 || { echo "nvcc not found: set CUDA_HOME or NVCC" >&2; exit 1; }
$(NVCC) $(NVCCFLAGS) backend_cuda.cu backend_cuda_test.cu -o backend_cuda_test
./backend_cuda_test
olmoe: olmoe.c st.h json.h
$(CC) $(CFLAGS) olmoe.c -o olmoe $(LDFLAGS)
@@ -41,4 +67,4 @@ portable:
$(MAKE) glm ARCH=x86-64-v3
clean:
rm -f olmoe glm
rm -f olmoe glm backend_cuda.o backend_cuda_test