thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

refactor : llama-model.cpp (#16252)

Browse source 
* Sqashed: llama-model.cpp refactoring

* Fix formatting of attn / ffn / ffn_moe calls

* Fix import regression / unify spacing in models.h

* totally DID NOT miss those!

* Add missing qwen3vl(moe) models

* Add missing new .cpp files to build

* Remove extra semicolons

* Editor checker

* Update src/models/models.h

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Piotr Wilkin (ilintar) 2025-10-31 23:40:23 +01:00 • committed by GitHub
parent 0de0a01576
commit bea04522ff
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
97 changed files with 13423 additions and 13563 deletions
Download patch file Download diff file Expand all files Collapse all files

55
src/models/mamba.cpp Normal file
View file

@ -0,0 +1,55 @@
#include "models.h"
llm_build_mamba::llm_build_mamba(const llama_model & model, const llm_graph_params & params) : llm_graph_context_mamba(params) {
ggml_tensor * cur;
ggml_tensor * inpL;
// {n_embd, n_tokens}
inpL = build_inp_embd(model.tok_embd);
auto * rs_inp = build_rs_inp();
ggml_tensor * inp_out_ids = build_inp_out_ids();
for (int il = 0; il < n_layer; ++il) {
// norm
cur = build_norm(inpL, model.layers[il].attn_norm, NULL, LLM_NORM_RMS, il);
cb(cur, "attn_norm", il);
if (model.arch == LLM_ARCH_MAMBA2) {
cur = build_mamba2_layer(rs_inp, cur, model, ubatch, il);
} else {
cur = build_mamba_layer(rs_inp, cur, model, ubatch, il);
}
if (il == n_layer - 1 && inp_out_ids) {
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
}
// residual
cur = ggml_add(ctx0, cur, inpL);
cur = build_cvec(cur, il);
cb(cur, "l_out", il);
// input for next layer
inpL = cur;
}
// final rmsnorm
cur = build_norm(inpL, model.output_norm, NULL, LLM_NORM_RMS, -1);
cb(cur, "result_norm", -1);
res->t_embd = cur;
// lm_head
cur = build_lora_mm(model.output, cur);
cb(cur, "result_output", -1);
res->t_logits = cur;
ggml_build_forward_expand(gf, cur);
}