Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
7 ヶ月 前 |
Georgi Gerganov
|
c3ee46fab4
batch : remove logits_all flag (#14141)
|
7 ヶ月 前 |
Georgi Gerganov
|
9596506965
kv-cache : fix split_equal handling in unified implementation (#14130)
|
7 ヶ月 前 |
Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
8 ヶ月 前 |
Georgi Gerganov
|
3e63a58ef7
kv-cache : refactor the update/defrag mechanism (#13988)
|
8 ヶ月 前 |
Georgi Gerganov
|
0fc16b42e8
kv-cache : split implementation in separate sources (#13920)
|
8 ヶ月 前 |