vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)

Browse source 
* add glm edge chat model

* use config partial_rotary_factor as rope ratio

* support for glm edge model

* vision model support

* remove debug info

* fix format

* llava.cpp trailing whitespace

* remove unused AutoTokenizer

* Update src/llama.cpp for not contain <|end|> or </s>

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* add edge template

* fix chat template

* fix confict

* fix confict

* fix ci err

* fix format err

* fix template err

* 9b hf chat support

* format

* format clip.cpp

* fix format

* Apply suggestions from code review

* Apply suggestions from code review

* Update examples/llava/clip.cpp

* fix format

* minor : style

---------

Co-authored-by: liyuhang <yuhang.li@zhipuai.cn>
Co-authored-by: piDack <pcdack@hotmail.co>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: liyuhang <yuhang.li@aminer.cn>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
piDack 2025-02-02 15:48:46 +08:00 • committed by GitHub
parent 53debe6f3c
commit 0cec062a63
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 568 additions and 67 deletions
Download patch file Download diff file Expand all files Collapse all files

35
src/llama.cpp
View file

@ -7215,17 +7215,30 @@ struct llm_build_context {
struct ggml_tensor * Qcur = nullptr;
struct ggml_tensor * Kcur = nullptr;
struct ggml_tensor * Vcur = nullptr;
cur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wqkv, cur);
cb(cur, "wqkv", il);
cur = ggml_add(ctx0, cur, model.layers[il].bqkv);
cb(cur, "bqkv", il);
Qcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd, n_tokens, cur->nb[1], 0*sizeof(float)*(n_embd)));
Kcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd)));
Vcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd + n_embd_gqa)));
if (model.type == LLM_TYPE_1_5B || model.type == LLM_TYPE_4B || model.type == LLM_TYPE_9B) {
Qcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wq, cur);
if (model.layers[il].bq) {
Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
}
Kcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wk, cur);
if (model.layers[il].bk) {
Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
}
Vcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wv, cur);
if (model.layers[il].bv) {
Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);
}
} else {
cur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wqkv, cur);
cb(cur, "wqkv", il);
if (model.layers[il].bqkv) {
cur = ggml_add(ctx0, cur, model.layers[il].bqkv);
cb(cur, "bqkv", il);
}
Qcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd, n_tokens, cur->nb[1], 0*sizeof(float)*(n_embd)));
Kcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd)));
Vcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd + n_embd_gqa)));
}
cb(Qcur, "Qcur", il);
cb(Kcur, "Kcur", il);
cb(Vcur, "Vcur", il);