thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

model: support youtu-vl model (#18479)

Browse source 
* Support Youtu-VL Model

* merge code

* fix bug

* revert qwen2 code & support rsplit in minja.hpp

* update warm info

* fix annotation

* u

* revert minja.hpp

* fix

* Do not write routed_scaling_factor to gguf when routed_scaling_factor is None

* fix expert_weights_scale

* LGTM after whitespace fixes

* fix

* fix

* fix

* layers to layer_index

* enum fix

---------

Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
tt 2026-01-02 02:25:54 +08:00 • committed by GitHub
parent 3ccccc83f7
commit ced765be44
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 473 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/models/deepseek2.cpp
View file

@ -215,7 +215,7 @@ llm_build_deepseek2::llm_build_deepseek2(const llama_model & model, const llm_gr
model.layers[il].ffn_exp_probs_b,
n_expert, n_expert_used,
LLM_FFN_SILU, hparams.expert_weights_norm,
true, hparams.expert_weights_scale,
hparams.expert_weights_scale, hparams.expert_weights_scale,
(llama_expert_gating_func_type) hparams.expert_gating_func,
il);
cb(moe_out, "ffn_moe_out", il);