ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 11:21:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Mimo-V2-Flash support (#1096)

Browse Source 
* Mimo-2 support

* Fix bug for head sizes not being the same

It still does not solve the Mimo-2 quantized cache issue.

* Fix quantized cache

* Minor

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2026-01-05 08:00:01 +02:00
committed by GitHub
parent 56dceefd6b
commit ab50c6cdcb
12 changed files with 251 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-hparams.h
View File

@@ -113,7 +113,7 @@ struct llama_hparams {
// qwen3vl deepstack
uint32_t n_deepstack_layers = 0;
// needed by encoder-decoder models (e.g. T5, FLAN-T5)
// ref: https://github.com/ggerganov/llama.cpp/pull/8141
llama_token dec_start_token_id = -1;
@@ -122,6 +122,8 @@ struct llama_hparams {
enum llama_rope_type rope_type = LLAMA_ROPE_TYPE_NONE;
enum llama_rope_scaling_type rope_scaling_type_train = LLAMA_ROPE_SCALING_TYPE_NONE;
std::array<uint32_t, LLAMA_MAX_LAYERS> swa_layers;
bool operator!=(const llama_hparams & other) const {
if (this->vocab_only != other.vocab_only) return true;
if (this->n_vocab != other.n_vocab) return true;