Georgi Gerganov
|
f6e1a7aa87
context : simplify output counting logic during decode (#14142)
|
7 months ago |
Georgi Gerganov
|
c3ee46fab4
batch : remove logits_all flag (#14141)
|
7 months ago |
Georgi Gerganov
|
12d0188c0d
kv-cache : refactor + add llama_memory_state_i (#13746)
|
8 months ago |
Georgi Gerganov
|
c642bc014c
kv-cache : separate recurrent vs non-recurrent impl (#12799)
|
8 months ago |
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
10 months ago |
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
1 year ago |