 Sigbjørn Skjæret
|
6385b843a8
llama : add RobertaForSequenceClassification reranker support (#13875)
|
8 ay önce |
 Georgi Gerganov
|
d13d0f6135
hparams : initialize arrays (#13728)
|
8 ay önce |
 Xuan-Son Nguyen
|
8a2afb7520
llama : allow custom list of swa_layers (#13726)
|
8 ay önce |
|
Georgi Gerganov
|
8e186ef0e7
hparams : support models for which all layers use SWA (#13682)
|
8 ay önce |
|
Georgi Gerganov
|
e298d2fbd0
kv-cache : add SWA support (#13194)
|
8 ay önce |
 AT
|
5f5e39e1ba
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (#12466)
|
9 ay önce |
 Juk Armstrong
|
daa422881a
llama : DeepSeek V2/V3 MLA implementation (#12801)
|
9 ay önce |
|
Xuan-Son Nguyen
|
1466621e73
llama : Support llama 4 text-only (#12791)
|
10 ay önce |
 Molly Sophia
|
7dfad387e3
llama: Add support for RWKV v7 architecture (#12412)
|
10 ay önce |
|
Georgi Gerganov
|
081bee8c64
hparams : add SWA rope parameters (#12374)
|
10 ay önce |
|
Georgi Gerganov
|
84d5475541
llama : fix Gemma3 SWA KV cache shift (#12373)
|
10 ay önce |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
1 yıl önce |
|
Molly Sophia
|
ee7136c6d1
llama: add support for QRWKV6 model architecture (#11001)
|
1 yıl önce |
 fairydreaming
|
9394bbd484
llama : Add support for DeepSeek V3 (#11049)
|
1 yıl önce |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 yıl önce |
