Xuan-Son Nguyen
|
1466621e73
llama : Support llama 4 text-only (#12791)
|
9 meses atrás |
Georgi Gerganov
|
75422e8bc4
graph : normalize Q, K, V shapes + sync cross attention (#12449)
|
10 meses atrás |
Georgi Gerganov
|
c522ce4143
graph : simplify attn input build for unified KV cache (#12381)
|
10 meses atrás |
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 meses atrás |