nwpie/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2026-02-05 13:53:23 +02:00
Code Issues Packages Projects Releases Wiki Activity

ggml : do not crash when quantizing q4_x_x with an imatrix (#9192)
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-rocm.Dockerfile platforms:linux/amd64,linux/arm64 tag:light-rocm]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-rocm.Dockerfile platforms:linux/amd64,linux/arm64 tag:server-rocm]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run

Browse Source
This commit is contained in:
slaren
2024-08-26 19:44:43 +02:00
committed by GitHub
parent 06658ad7c3
commit 7d787ed96c
1 changed files with 6 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
ggml/src/ggml-aarch64.c
View File

@@ -337,33 +337,18 @@ static size_t quantize_q4_0_nr_bl(const float * restrict src, void * restrict ds
}
size_t quantize_q4_0_4x4(const float * restrict src, void * restrict dst, int64_t nrow, int64_t n_per_row, const float * quant_weights) {
if (!quant_weights) {
return quantize_q4_0_nr_bl(src, dst, nrow, n_per_row, 4, 4);
}
else {
assert(false);
return 0;
}
UNUSED(quant_weights);
return quantize_q4_0_nr_bl(src, dst, nrow, n_per_row, 4, 4);
}
size_t quantize_q4_0_4x8(const float * restrict src, void * restrict dst, int64_t nrow, int64_t n_per_row, const float * quant_weights) {
if (!quant_weights) {
return quantize_q4_0_nr_bl(src, dst, nrow, n_per_row, 4, 8);
}
else {
assert(false);
return 0;
}
UNUSED(quant_weights);
return quantize_q4_0_nr_bl(src, dst, nrow, n_per_row, 4, 8);
}
size_t quantize_q4_0_8x8(const float * restrict src, void * restrict dst, int64_t nrow, int64_t n_per_row, const float * quant_weights) {
if (!quant_weights) {
return quantize_q4_0_nr_bl(src, dst, nrow, n_per_row, 8, 8);
}
else {
assert(false);
return 0;
}
UNUSED(quant_weights);
return quantize_q4_0_nr_bl(src, dst, nrow, n_per_row, 8, 8);
}
void ggml_gemv_q4_0_4x4_q8_0(int n, float * restrict s, size_t bs, const void * restrict vx, const void * restrict vy, int nr, int nc) {