Georgi Gerganov
|
c79184d2d1
batch : add n_used count (#14512)
|
6 months ago |
Georgi Gerganov
|
a70c8a0c4b
kv-cache : use ggml_set_rows (#14285)
|
6 months ago |
Georgi Gerganov
|
745f11fed0
memory : correctly handle failure in apply() (#14438)
|
6 months ago |
Xuan-Son Nguyen
|
8846aace49
model : gemma3n text-only (#14400)
|
6 months ago |
Georgi Gerganov
|
692e3cdd0a
memory : rename interface to llama_memory_context_i (#14296)
|
7 months ago |
Georgi Gerganov
|
4c9fdfbe15
ubatch : new splitting logic (#14217)
|
7 months ago |
Gabe Goodhart
|
edc4a29eff
memory : Hybrid recurrent cache (#13979)
|
7 months ago |
Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
7 months ago |
Georgi Gerganov
|
5fce5f948d
kv-cache : fix use-after-move of defrag info (#14189)
|
7 months ago |
Georgi Gerganov
|
c311ac664d
cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)
|
7 months ago |
Georgi Gerganov
|
60c666347b
batch : rework llama_batch_allocr (#14153)
|
7 months ago |
Georgi Gerganov
|
c3ee46fab4
batch : remove logits_all flag (#14141)
|
7 months ago |
Georgi Gerganov
|
9596506965
kv-cache : fix split_equal handling in unified implementation (#14130)
|
7 months ago |
Georgi Gerganov
|
89a184fa71
kv-cache : relax SWA masking condition (#14119)
|
7 months ago |
Georgi Gerganov
|
7ae2932116
kv-cache : add LLAMA_KV_CACHE_DEBUG environment variable (#14121)
|
7 months ago |
compilade
|
dad5c44398
kv-cache : avoid modifying recurrent cells when setting inputs (#13834)
|
7 months ago |
Georgi Gerganov
|
40cbf571c9
kv-cache : fix shift and defrag logic (#14081)
|
7 months ago |
Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
7 months ago |
Georgi Gerganov
|
3e63a58ef7
kv-cache : refactor the update/defrag mechanism (#13988)
|
7 months ago |
Georgi Gerganov
|
e0e806f52e
kv-cache : fix unified::seq_rm to work with seq_id < 0 (#13985)
|
7 months ago |
Georgi Gerganov
|
0fc16b42e8
kv-cache : split implementation in separate sources (#13920)
|
7 months ago |