 Georgi Gerganov
|
75422e8bc4
graph : normalize Q, K, V shapes + sync cross attention (#12449)
|
10 сар өмнө |
 fairydreaming
|
8fcb563613
Load all MoE experts during warmup (#11571)
|
10 сар өмнө |
|
Georgi Gerganov
|
c522ce4143
graph : simplify attn input build for unified KV cache (#12381)
|
10 сар өмнө |
|
Georgi Gerganov
|
081bee8c64
hparams : add SWA rope parameters (#12374)
|
10 сар өмнө |
|
Georgi Gerganov
|
84d5475541
llama : fix Gemma3 SWA KV cache shift (#12373)
|
10 сар өмнө |
|
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 сар өмнө |
