fairydreaming 82dbc4f017 llama : load MTP tensors only if they are really used (#26296) ... * llama : load MTP tensors only if they are really used * llama : skip loading MTP (if not used) in remaining models that support MTP --------- Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>		2026-07-31 14:57:02 +02:00
..
afmoe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
apertus.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
arcee.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
arctic.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
arwkv7.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
baichuan.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
bailingmoe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
bailingmoe2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
bert.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
bitnet.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
bloom.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
chameleon.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
chatglm.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
codeshell.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
cogvlm.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
cohere2.cpp	Add arch support for cohere2-MoE (#24260)	2026-06-13 19:49:00 +02:00
cohere2moe.cpp	llama : load MTP tensors only if they are really used (#26296)	2026-07-31 14:57:02 +02:00
command-r.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
dbrx.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
deci.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
deepseek.cpp	model : NvFP4 quantized LM head support (#23046)	2026-05-16 11:09:27 +02:00
deepseek2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
deepseek2ocr.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
deepseek4.cpp	ggml : adjust logic for offloading ops to weight's backend (#25832)	2026-07-27 14:54:46 +03:00
deepseek32.cpp	ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231)	2026-07-11 11:39:07 +02:00
delta-net-base.cpp	llama: refactor fused ops (#24646)	2026-07-08 18:18:09 +08:00
dflash.cpp	spec: add DSpark speculative decoding (#25173)	2026-07-28 14:43:27 +03:00
dots1.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
dream.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
eagle3.cpp	spec: add eagle3-v3 support for gpt-oss model (#25794)	2026-07-28 09:58:16 +03:00
ernie4-5-moe.cpp	model : NvFP4 quantized LM head support (#23046)	2026-05-16 11:09:27 +02:00
ernie4-5.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
eurobert.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
exaone-moe.cpp	minor : fix lint issues (#24165)	2026-06-05 11:17:54 +03:00
exaone.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
exaone4.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
falcon-h1.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
falcon.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
gemma-embedding.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
gemma.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
gemma2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
gemma3.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
gemma3n.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
gemma4-assistant.cpp	mtp: support for gemma-4 E2B and E4B assistants (#24282)	2026-06-08 13:48:52 -07:00
gemma4.cpp	llama: move suppress_tokens handling to common/sampling (#26276)	2026-07-29 18:02:30 +02:00
glm-dsa.cpp	llama : load MTP tensors only if they are really used (#26296)	2026-07-31 14:57:02 +02:00
glm4-moe.cpp	minor : fix lint issues (#24165)	2026-06-05 11:17:54 +03:00
glm4.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
gpt2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
gptneox.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
granite-hybrid.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
granite-moe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
granite.cpp	model, mtmd: Granite4 Vision (#23545)	2026-06-05 17:44:59 +02:00
grok.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
grovemoe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
hunyuan-dense.cpp	model: move load_hparams and load_tensors to per-model definition (#22004)	2026-05-04 12:36:59 +02:00
hunyuan-moe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
hunyuan-vl.cpp	model : NvFP4 quantized LM head support (#23046)	2026-05-16 11:09:27 +02:00
hy-v3.cpp	llama : load MTP tensors only if they are really used (#26296)	2026-07-31 14:57:02 +02:00
internlm2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
jais.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
jais2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
jamba.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
jina-bert-v2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
jina-bert-v3.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
kimi-linear.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
laguna.cpp	model: Add Laguna-S-2.1 LLM_TYPE (#26233)	2026-07-28 21:02:33 +02:00
lfm2.cpp	model : Add label for LFM2.5-230M (#25008)	2026-06-25 18:58:52 +02:00
lfm2moe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
llada-moe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
llada.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
llama-embed.cpp	model: move load_hparams and load_tensors to per-model definition (#22004)	2026-05-04 12:36:59 +02:00
llama.cpp	spec: add EAGLE3 speculative decoding support (#18039)	2026-06-12 10:21:06 +03:00
llama4.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
maincoder.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
mamba-base.cpp	mamba2: remove hardcoded 2x expansion factor and invalid d_inner % d_state check (#23082)	2026-06-26 08:50:54 +03:00
mamba.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
mamba2.cpp	mamba2: remove hardcoded 2x expansion factor and invalid d_inner % d_state check (#23082)	2026-06-26 08:50:54 +03:00
mellum.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
mimo2.cpp	mimo2: address MTP review feedback (#26228)	2026-07-30 11:55:58 +08:00
minicpm.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
minicpm3.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
minimax-m2.cpp	spec: add Minimax2 eagle3 support	2026-07-13 15:22:37 +02:00
minimax-m3.cpp	Remove custom cpu op from the M3 graph, express with stock ops (#26297)	2026-07-30 16:30:18 +08:00
mistral3.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
mistral4.cpp	model: move load_hparams and load_tensors to per-model definition (#22004)	2026-05-04 12:36:59 +02:00
models.h	mimo2: address MTP review feedback (#26228)	2026-07-30 11:55:58 +08:00
modern-bert.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
mpt.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
nanbeige.cpp	model: Add support for Nanbeige4.2 (#25994)	2026-07-27 17:04:18 +02:00
nemotron-h-moe.cpp	model: move load_hparams and load_tensors to per-model definition (#22004)	2026-05-04 12:36:59 +02:00
nemotron-h.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
nemotron.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
neo-bert.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
nomic-bert-moe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
nomic-bert.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
olmo.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
olmo2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
olmoe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
openai-moe.cpp	spec: add eagle3-v3 support for gpt-oss model (#25794)	2026-07-28 09:58:16 +03:00
openelm.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
orion.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
paddleocr.cpp	model : NvFP4 quantized LM head support (#23046)	2026-05-16 11:09:27 +02:00
pangu-embed.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
phi2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
phi3.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
phimoe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
plamo.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
plamo2.cpp	models : fix plamo2 attention_key/value_length regression (#24317)	2026-06-09 10:26:44 +03:00
plamo3.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
plm.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
qwen.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
qwen2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
qwen2moe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
qwen2vl.cpp	model : NvFP4 quantized LM head support (#23046)	2026-05-16 11:09:27 +02:00
qwen3.cpp	spec: add EAGLE3 speculative decoding support (#18039)	2026-06-12 10:21:06 +03:00
qwen3moe.cpp	spec: add EAGLE3 speculative decoding support (#18039)	2026-06-12 10:21:06 +03:00
qwen3next.cpp	model : register t_layer_inp for qwen3next (#25141)	2026-06-30 17:57:14 +02:00
qwen3vl.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
qwen3vlmoe.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
qwen35.cpp	llama : load MTP tensors only if they are really used (#26296)	2026-07-31 14:57:02 +02:00
qwen35moe.cpp	llama : load MTP tensors only if they are really used (#26296)	2026-07-31 14:57:02 +02:00
refact.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
rnd1.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
rwkv6-base.cpp	models : deduplicate delta-net graphs for Qwen family (#19597)	2026-02-16 14:35:04 +02:00
rwkv6.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
rwkv6qwen2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
rwkv7-base.cpp	models : deduplicate delta-net graphs for Qwen family (#19597)	2026-02-16 14:35:04 +02:00
rwkv7.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
seed-oss.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
smallthinker.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
smollm3.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
stablelm.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
starcoder.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
starcoder2.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
step35.cpp	llama : load MTP tensors only if they are really used (#26296)	2026-07-31 14:57:02 +02:00
t5.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
t5encoder.cpp	model: move load_hparams and load_tensors to per-model definition (#22004)	2026-05-04 12:36:59 +02:00
talkie.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00
wavtokenizer-dec.cpp	model : NvFP4 quantized LM head support (#23046)	2026-05-16 11:09:27 +02:00
xverse.cpp	hparams : refactor hparams.n_layer (#24060)	2026-06-05 11:09:36 +03:00