| .. |
|
afmoe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
apertus.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
arcee.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
arctic.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
arwkv7.cpp
|
refactor : llama-model.cpp (#16252)
|
2025-10-31 23:40:23 +01:00 |
|
baichuan.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
bailingmoe.cpp
|
graph : remove redundant scale_w parameter (#20235)
|
2026-03-08 18:58:28 +01:00 |
|
bailingmoe2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
bert.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
bitnet.cpp
|
graph : add optional scale parameter to build_lora_mm [no ci] (#20427)
|
2026-03-12 00:22:49 +01:00 |
|
bloom.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
chameleon.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
chatglm.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
codeshell.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
cogvlm.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
cohere2-iswa.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
command-r.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
dbrx.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
deci.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
deepseek.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
deepseek2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
delta-net-base.cpp
|
graph : remove redundant GDN state transposes (#20443)
|
2026-03-13 22:12:54 +02:00 |
|
dots1.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
dream.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
ernie4-5-moe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
ernie4-5.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
eurobert.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
exaone-moe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
exaone.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
exaone4.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
falcon-h1.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
falcon.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
gemma-embedding.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
gemma.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
gemma2-iswa.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
gemma3.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
gemma3n-iswa.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
glm4-moe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
glm4.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
gpt2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
gptneox.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
granite-hybrid.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
granite.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
grok.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
grovemoe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
hunyuan-dense.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
hunyuan-moe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
internlm2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
jais.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
jais2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
jamba.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
kimi-linear.cpp
|
llama : enable chunked fused GDN path (#20340)
|
2026-03-11 22:46:40 +02:00 |
|
lfm2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
llada-moe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
llada.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
llama-iswa.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
llama.cpp
|
graph : add optional scale parameter to build_lora_mm [no ci] (#20427)
|
2026-03-12 00:22:49 +01:00 |
|
maincoder.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
mamba-base.cpp
|
model : wire up Nemotron-H tensors for NVFP4 support (#20561)
|
2026-03-16 09:19:16 +01:00 |
|
mamba.cpp
|
models : deduplicate delta-net graphs for Qwen family (#19597)
|
2026-02-16 14:35:04 +02:00 |
|
mimo2-iswa.cpp
|
graph : remove redundant scale_w parameter (#20235)
|
2026-03-08 18:58:28 +01:00 |
|
minicpm3.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
minimax-m2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
mistral3.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
models.h
|
llama : enable chunked fused GDN path (#20340)
|
2026-03-11 22:46:40 +02:00 |
|
modern-bert.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
mpt.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
nemotron-h.cpp
|
model : wire up Nemotron-H tensors for NVFP4 support (#20561)
|
2026-03-16 09:19:16 +01:00 |
|
nemotron.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
neo-bert.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
olmo.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
olmo2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
olmoe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
openai-moe-iswa.cpp
|
graph : remove redundant scale_w parameter (#20235)
|
2026-03-08 18:58:28 +01:00 |
|
openelm.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
orion.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
paddleocr.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
pangu-embedded.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
phi2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
phi3.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
plamo.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
plamo2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
plamo3.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
plm.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
qwen.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
qwen2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
qwen2moe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
qwen2vl.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
qwen3.cpp
|
graph : add optional scale parameter to build_lora_mm [no ci] (#20427)
|
2026-03-12 00:22:49 +01:00 |
|
qwen3moe.cpp
|
graph : add optional scale parameter to build_lora_mm [no ci] (#20427)
|
2026-03-12 00:22:49 +01:00 |
|
qwen3next.cpp
|
llama : enable chunked fused GDN path (#20340)
|
2026-03-11 22:46:40 +02:00 |
|
qwen3vl-moe.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
qwen3vl.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
qwen35.cpp
|
model : wire up Qwen3.5/Qwen3.5MoE tensors for NVFP4 support (#20506)
|
2026-03-14 22:44:42 +01:00 |
|
qwen35moe.cpp
|
model : wire up Qwen3.5/Qwen3.5MoE tensors for NVFP4 support (#20506)
|
2026-03-14 22:44:42 +01:00 |
|
refact.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
rnd1.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
rwkv6-base.cpp
|
models : deduplicate delta-net graphs for Qwen family (#19597)
|
2026-02-16 14:35:04 +02:00 |
|
rwkv6.cpp
|
refactor : llama-model.cpp (#16252)
|
2025-10-31 23:40:23 +01:00 |
|
rwkv6qwen2.cpp
|
refactor : llama-model.cpp (#16252)
|
2025-10-31 23:40:23 +01:00 |
|
rwkv7-base.cpp
|
models : deduplicate delta-net graphs for Qwen family (#19597)
|
2026-02-16 14:35:04 +02:00 |
|
rwkv7.cpp
|
refactor : llama-model.cpp (#16252)
|
2025-10-31 23:40:23 +01:00 |
|
seed-oss.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
smallthinker.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
smollm3.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
stablelm.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
starcoder.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
starcoder2.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
step35-iswa.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
t5-dec.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
t5-enc.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
|
wavtokenizer-dec.cpp
|
chore : fix models indent after refactor (#16992)
|
2025-11-04 12:29:15 +01:00 |
|
xverse.cpp
|
llama: dynamic head_dim and n_rot for SWA (#20301)
|
2026-03-09 22:22:39 +01:00 |
de8f01c2d7