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

ggml : remove old quantization functions (#5942)

Browse source 
* ggml : remove old quantization functions

ggml-ci

* ggml : simplify ggml_quantize_chunk

ggml-ci

* ggml : restrict correctness

ggml-ci

* ggml : remove hist data from the quantization API

ggml-ci

* tests : remove hist usage in test-backend-ops

ggml-ci

* vulkan : remove hist and fix typo
This commit is contained in:
Georgi Gerganov 2024-03-09 15:53:59 +02:00 • committed by GitHub
parent 97c09585d6
commit 5b09797321
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 131 additions and 568 deletions
Download patch file Download diff file Expand all files Collapse all files

3
tests/test-backend-ops.cpp
View file

@ -53,7 +53,6 @@ static void init_tensor_uniform(ggml_tensor * tensor, float min = -1.0f, float m
} else if (ggml_is_quantized(tensor->type) || tensor->type == GGML_TYPE_F16) {
GGML_ASSERT(size % ggml_blck_size(tensor->type) == 0);
std::vector<uint8_t> dataq(ggml_row_size(tensor->type, size));
int64_t hist[16];
std::vector<float> imatrix(tensor->ne[0], 1.0f); // dummy importance matrix
const float * im = imatrix.data();
if (!ggml_quantize_requires_imatrix(tensor->type)) {
@ -63,7 +62,7 @@ static void init_tensor_uniform(ggml_tensor * tensor, float min = -1.0f, float m
im = nullptr;
}
}
ggml_quantize_chunk(tensor->type, data.data(), dataq.data(), 0, size/tensor->ne[0], tensor->ne[0], hist, im);
ggml_quantize_chunk(tensor->type, data.data(), dataq.data(), 0, size/tensor->ne[0], tensor->ne[0], im);
ggml_backend_tensor_set(tensor, dataq.data(), 0, dataq.size());
} else if (tensor->type == GGML_TYPE_I8 || tensor->type == GGML_TYPE_I16 || tensor->type == GGML_TYPE_I32) {
// This is going to create some weird integers though.