ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Refactor lora adapter support (#8332)

Browse source 
* lora: load to devide buft

* add patch tensor function

* correct tensor patch

* llama_lora_adapter_apply

* correct ggml_backend_tensor_copy

* add llm_build_mm

* fix auto merge

* update based on review comments

* add convert script

* no more transpose A

* add f16 convert

* add metadata check

* add sanity check

* fix ftype

* add requirements

* fix requirements

* fix outfile

* conversion: only allow selected models

* fix types

* cuda : do not use dmmv if the tensor does not have enough cols

* llama : lora fixes

* do not disable mmap with lora

Co-authored-by: slaren <slarengh@gmail.com>

* llm_build_lora_mm_id

* convert_lora : MoE LoRA conversion support

* convert_lora : prefer safetensors, similarly to convert_hf

* convert_hf : simplify modify_tensors for InternLM2

* convert_lora : lazy conversion

* llama : load and use alpha from LoRA adapters

* llama : use llm_build_lora_mm in most model graphs

* auto scale

* Revert "auto scale"

This reverts commit 42415a4874e0f963e4aca6796ea5dfb97cd17464.

* remove redundant params

* Apply suggestions from code review

Co-authored-by: slaren <slarengh@gmail.com>

* change kv metadata

* move add_type to __init__

* convert_hf : move add_type to main()

* convert_lora : use the GGUFWriter from Model instead of overwriting it

---------

Co-authored-by: slaren <slarengh@gmail.com>
Co-authored-by: Francis Couture-Harpin <git@compilade.net>
This commit is contained in:
Xuan Son Nguyen 2024-07-15 20:50:47 +02:00 • committed by GitHub
parent 4db8f60fe7
commit 97bdd26eee
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 963 additions and 530 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml/src/ggml-cuda.cu
View file

@ -1876,7 +1876,8 @@ static void ggml_cuda_mul_mat(ggml_backend_cuda_context & ctx, const ggml_tensor
bool use_dequantize_mul_mat_vec = (ggml_is_quantized(src0->type) || src0->type == GGML_TYPE_F16)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
&& src0->ne[0] % GGML_CUDA_DMMV_X == 0 && src1->ne[1] == 1;
&& src0->ne[0] % GGML_CUDA_DMMV_X == 0 && src0->ne[0] >= GGML_CUDA_DMMV_X*2
&& src1->ne[1] == 1;
bool use_mul_mat_vec_q = ggml_is_quantized(src0->type)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
&& src1->ne[1] <= MMVQ_MAX_BATCH_SIZE;