vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : add asserts to guard for incorrect wsize

Browse source
This commit is contained in:
Georgi Gerganov 2023-04-29 14:26:36 +03:00
parent 0ffcd89870
commit 658c686e5a
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
2 changed files with 15 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
Makefile
View file

@ -34,10 +34,15 @@ endif
#
# keep standard at C11 and C++11
CFLAGS = -I. -O3 -DNDEBUG -std=c11 -fPIC
CXXFLAGS = -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC
CFLAGS = -I. -O3 -std=c11 -fPIC
CXXFLAGS = -I. -I./examples -O3 -std=c++11 -fPIC
LDFLAGS =
ifndef LLAMA_DEBUG
CFLAGS += -DNDEBUG
CXXFLAGS += -DNDEBUG
endif
# warnings
CFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith
CXXFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar

10
ggml.c
View file

@ -8245,8 +8245,6 @@ static void ggml_compute_forward_mul_mat_f16_f32(
ggml_fp16_t * d_X = ggml_cuda_pool_malloc(sizeof(float) * x_ne, &x_size);
ggml_fp16_t * d_Y = ggml_cuda_pool_malloc(sizeof(float) * y_ne, &y_size);
float * d_D = ggml_cuda_pool_malloc(sizeof(float) * d_ne, &d_size);
#else
float * const wdata = params->wdata;
#endif
for (int64_t i03 = 0; i03 < ne03; i03++) {
for (int64_t i02 = 0; i02 < ne02; i02++) {
@ -8263,8 +8261,11 @@ static void ggml_compute_forward_mul_mat_f16_f32(
wdata[id++] = GGML_FP32_TO_FP16(*(float *) ((char *) src1->data + i03*nb13 + i02*nb12 + i01*nb11 + i00*nb10));
}
}
assert(id*sizeof(ggml_fp16_t) <= params->wsize);
}
#else
float * const wdata = params->wdata;
{
size_t id = 0;
for (int64_t i01 = 0; i01 < ne01; ++i01) {
@ -8272,6 +8273,8 @@ static void ggml_compute_forward_mul_mat_f16_f32(
wdata[id++] = GGML_FP16_TO_FP32(*(ggml_fp16_t *) ((char *) src0->data + i03*nb03 + i02*nb02 + i01*nb01 + i00*nb00));
}
}
assert(id*sizeof(float) <= params->wsize);
}
#endif
@ -8537,7 +8540,10 @@ static void ggml_compute_forward_mul_mat_q_f32(
dequantize_row_q((char *) src0->data + i03*nb03 + i02*nb02 + i01*nb01, wdata + id, ne00);
id += ne00;
}
assert(id*sizeof(float) <= params->wsize);
}
const float * x = wdata;
#endif