 Georgi Gerganov
|
67d1ef23c6
batch : add optional for sequential equal split (#14511)
|
hai 6 meses |
|
Georgi Gerganov
|
c79184d2d1
batch : add n_used count (#14512)
|
hai 6 meses |
|
Georgi Gerganov
|
4c9fdfbe15
ubatch : new splitting logic (#14217)
|
hai 7 meses |
|
Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
hai 7 meses |
|
Georgi Gerganov
|
b9912ac570
batch : auto-gen positions + verify multi-sequence input (#14177)
|
hai 7 meses |
|
Georgi Gerganov
|
80709b70a2
batch : add LLAMA_BATCH_DEBUG environment variable (#14172)
|
hai 7 meses |
|
Georgi Gerganov
|
60c666347b
batch : rework llama_batch_allocr (#14153)
|
hai 7 meses |
|
Georgi Gerganov
|
f6e1a7aa87
context : simplify output counting logic during decode (#14142)
|
hai 7 meses |
|
Georgi Gerganov
|
c3ee46fab4
batch : remove logits_all flag (#14141)
|
hai 7 meses |
|
Georgi Gerganov
|
12d0188c0d
kv-cache : refactor + add llama_memory_state_i (#13746)
|
hai 8 meses |
|
Georgi Gerganov
|
c642bc014c
kv-cache : separate recurrent vs non-recurrent impl (#12799)
|
hai 8 meses |
|
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
hai 10 meses |
|
Georgi Gerganov
|
f66f582927
llama : refactor `src/llama.cpp` (#10902)
|
hai 1 ano |
