 Georgi Gerganov
|
d498af3d5a
graph : avoid huge warm-up graphs for MoE models (#14753)
|
6 месяцев назад |
|
Georgi Gerganov
|
8f974bc1e9
graph : refactor context to not pass gf explicitly (#14629)
|
6 месяцев назад |
|
Georgi Gerganov
|
01612b7409
llama : reuse compute graphs (#14482)
|
6 месяцев назад |
|
Georgi Gerganov
|
225e7a1438
llama : add high-throughput mode (#14363)
|
6 месяцев назад |
 Aman Gupta
|
9c9e4fc635
llama-context: add ability to get logits (#14672)
|
6 месяцев назад |
|
Georgi Gerganov
|
7b50d589a8
kv-cells : fix tracking of seq_pos (#14339)
|
6 месяцев назад |
|
Georgi Gerganov
|
692e3cdd0a
memory : rename interface to llama_memory_context_i (#14296)
|
7 месяцев назад |
|
Georgi Gerganov
|
4c9fdfbe15
ubatch : new splitting logic (#14217)
|
7 месяцев назад |
|
Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
7 месяцев назад |
|
Georgi Gerganov
|
c311ac664d
cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)
|
7 месяцев назад |
|
Georgi Gerganov
|
b9912ac570
batch : auto-gen positions + verify multi-sequence input (#14177)
|
7 месяцев назад |
|
Georgi Gerganov
|
60c666347b
batch : rework llama_batch_allocr (#14153)
|
7 месяцев назад |
|
Georgi Gerganov
|
f6e1a7aa87
context : simplify output counting logic during decode (#14142)
|
7 месяцев назад |
|
Georgi Gerganov
|
c3ee46fab4
batch : remove logits_all flag (#14141)
|
7 месяцев назад |
|
Georgi Gerganov
|
9596506965
kv-cache : fix split_equal handling in unified implementation (#14130)
|
7 месяцев назад |
 compilade
|
a20b2b05bc
context : round n_tokens to next multiple of n_seqs when reserving (#14140)
|
7 месяцев назад |
|
Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
7 месяцев назад |
|
Georgi Gerganov
|
487a5e0401
context : fix SWA-related warning for multiple sequences (#14045)
|
7 месяцев назад |
 Sigbjørn Skjæret
|
d17a809ef0
llama : support multiple classifier outputs and labels (#13940)
|
7 месяцев назад |
|
Georgi Gerganov
|
7f37b6cf1e
memory : migrate from llama_kv_cache to more generic llama_memory (#14006)
|
7 месяцев назад |
|
Georgi Gerganov
|
9e31bec4fd
context : fix pos_min initialization upon error decode (#14008)
|
7 месяцев назад |
|
Georgi Gerganov
|
3e63a58ef7
kv-cache : refactor the update/defrag mechanism (#13988)
|
7 месяцев назад |
|
Georgi Gerganov
|
803f8baf4f
llama : deprecate explicit kv_self defrag/update calls (#13921)
|
7 месяцев назад |
|
Georgi Gerganov
|
3600cc2886
llama : use n_swa + n_ubatch cells for SWA cache (#13833)
|
7 месяцев назад |
|
Georgi Gerganov
|
3f55f781f1
llama : auto-batch preparation (#13845)
|
7 месяцев назад |
|
Georgi Gerganov
|
12d0188c0d
kv-cache : refactor + add llama_memory_state_i (#13746)
|
7 месяцев назад |
|
Georgi Gerganov
|
4f81b33e32
llama : validate seq id batch input (#13809)
|
7 месяцев назад |
|
Georgi Gerganov
|
79c137f776
examples : allow extracting embeddings from decoder contexts (#13797)
|
7 месяцев назад |
|
Georgi Gerganov
|
de2ef53a4b
kv-cache : rework kv_cell (#13706)
|
7 месяцев назад |
|
Georgi Gerganov
|
797f2ac062
kv-cache : simplify the interface (#13660)
|
8 месяцев назад |
