wylab/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-06 17:57:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

model: M3: Move MSA into a new memory implementation (#26338)

Browse Source 
* Move MSA logic from llama-kv-cache into llama-kv-cache-msa

* cont : minor

* cont : ws fix

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
timkhronos
2026-08-03 16:30:08 +03:00
committed by GitHub
co-authored by Georgi Gerganov
parent 563dec81c1
commit 67d5978bb1
11 changed files with 826 additions and 378 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-hparams.cpp
-10
View File
@@ -180,16 +180,6 @@ uint32_t llama_hparams::n_embd_v_gqa_max() const {
return val;
}
uint32_t llama_hparams::n_embd_k_idx(uint32_t il) const {
if (!indexer_kv || indexer_head_size == 0) {
return 0; // arch without a MSA indexer
}
if (il < n_layer_dense_lead) {
return 0; // leading dense layers carry no indexer
}
return indexer_head_size; // 128
}
uint32_t llama_hparams::n_embd_r() const {
if (wkv_head_size != 0) {
// for RWKV models