 AT
|
5f5e39e1ba
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (#12466)
|
8 mesiacov pred |
 Juk Armstrong
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
9 mesiacov pred |
 Yuxuan Zhang
|
06bb53ad9b
llama-model : add Glm4Model implementation for GLM-4-0414 (#12867)
|
9 mesiacov pred |
 Bo Zheng
|
d3bd7193ba
llama : Support Qwen3 and Qwen3MoE (#12828)
|
9 mesiacov pred |
 Xuan-Son Nguyen
|
1466621e73
llama : Support llama 4 text-only (#12791)
|
9 mesiacov pred |
 jklincn
|
e39e727e9a
llama : use LLM_KV_GENERAL_FILE_TYPE instead of gguf_find_key (#12672)
|
9 mesiacov pred |
 Sigbjørn Skjæret
|
2c3f8b850a
llama : support BailingMoE (Ling) (#12634)
|
9 mesiacov pred |
 Si1w
|
f125b8dccf
llama : add PLM GGUF Conversion & Inference Support (#12457)
|
9 mesiacov pred |
|
Xuan-Son Nguyen
|
fbdfefe74e
llama : gemma3 : use output tensor if it exists in model weight (#12506)
|
10 mesiacov pred |
 Molly Sophia
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
10 mesiacov pred |
|
Xuan-Son Nguyen
|
7841fc723e
llama : Add Gemma 3 support (+ experimental vision capability) (#12343)
|
10 mesiacov pred |
 piDack
|
0cec062a63
llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
|
11 mesiacov pred |
 Olivier Chafik
|
6171c9d258
Add Jinja template support (#11016)
|
1 rok pred |
 Xuan Son Nguyen
|
9a483999a6
llama : fix chat template gguf key (#11201)
|
1 rok pred |
 Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 rok pred |
|
Molly Sophia
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 rok pred |
 Pierrick Hymbert
|
f8feb4b01a
model: Add support for PhiMoE arch (#11003)
|
1 rok pred |
 fairydreaming
|
9394bbd484
llama : Add support for DeepSeek V3 (#11049)
|
1 rok pred |
 DAN™
|
46be942214
llama : add support for the cohere2 model architecture (#10900)
|
1 rok pred |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 rok pred |
