tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 11:45:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

quantize: Handle user-defined quantization levels for additional tensors (#12511)

Browse Source 
* Add llama_model_quantize_params parameters

* Add new quantize parameters parsing and validation

* Update usage

* Add new parameters defaults

* Add new quantization parameters logic

* Add llama_model_quantize_params parameters

* Add new quantize parameters parsing and validation

* Update usage

* Add new parameters defaults

* Add new quantization parameters logic

* Minor refactoring as per the contributors' coding guidelines

* Update descriptions to match existing style

* Add llama_model_quantize_params parameters

* Add new quantize parameters parsing and validation

* Update usage

* Add new parameters defaults

* Add new quantization parameters logic

* Minor refactoring as per the contributors' guidelines

* Implement general --tensor-type instead of tensor-specific command option

* Fix implied type bug

* Restore missing #includes

* Add regex capability for tensor selection

* Refactor function name and update ALLOWED_TENSOR_TYPE

* Add missing #include

* Handle edge case when tensor name is cls.output

* Minor logging improvement
This commit is contained in:
Ed Addario
2025-04-13 19:29:28 +01:00
committed by GitHub
parent bc091a4dc5
commit 71e90e8813
3 changed files with 155 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
include/llama.h
View File

@ -367,17 +367,18 @@ extern "C" {
// model quantization parameters
typedef struct llama_model_quantize_params {
int32_t nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
enum llama_ftype ftype; // quantize to this llama_ftype
enum ggml_type output_tensor_type; // output tensor type
enum ggml_type token_embedding_type; // token embeddings tensor type
bool allow_requantize; // allow quantizing non-f32/f16 tensors
bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
bool pure; // quantize all tensors to the default type
bool keep_split; // quantize to the same number of shards
void * imatrix; // pointer to importance matrix data
void * kv_overrides; // pointer to vector containing overrides
int32_t nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
enum llama_ftype ftype; // quantize to this llama_ftype
enum ggml_type output_tensor_type; // output tensor type
enum ggml_type token_embedding_type; // token embeddings tensor type
bool allow_requantize; // allow quantizing non-f32/f16 tensors
bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
bool pure; // quantize all tensors to the default type
bool keep_split; // quantize to the same number of shards
void * imatrix; // pointer to importance matrix data
void * kv_overrides; // pointer to vector containing overrides
void * tensor_types; // pointer to vector containing tensor types
} llama_model_quantize_params;
typedef struct llama_logit_bias {