tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-21 07:03:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

model : add support for SmallThinker series (#14898)

Browse Source 
* support smallthinker

* support 20b softmax, 4b no sliding window

* new build_moe_ffn_from_probs, and can run 4b

* fix 4b rope bug

* fix python type check

* remove is_moe judge

* remove set_dense_start_swa_pattern function and modify set_swa_pattern function

* trim trailing whitespace

* remove get_vocab_base of SmallThinkerModel in convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* better whitespace

Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* use GGML_ASSERT for expert count validation

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Improve null pointer check for probs

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* use template parameter for SWA attention logic

* better whitespace

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* move the creation of inp_out_ids before the layer loop

* remove redundant judge for probs

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Dongliang Wei
2025-07-28 19:47:00 +08:00
committed by GitHub
parent afc0e89698
commit 6c6e397aff
10 changed files with 443 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/llama-graph.h
View File

@@ -625,6 +625,18 @@ struct llm_graph_context {
llama_expert_gating_func_type gating_op,
int il) const;
ggml_tensor * build_moe_ffn_from_probs(
ggml_tensor * cur,
ggml_tensor * probs,
ggml_tensor * up_exps,
ggml_tensor * gate_exps,
ggml_tensor * down_exps,
ggml_tensor * exp_probs_b,
int64_t n_expert,
int64_t n_expert_used,
llama_expert_gating_func_type gating_op,
int il) const;
//
// inputs
//