 Georgi Gerganov
|
663027fd54
context : fix n_outputs during reserve (#15858)
|
4 months ago |
 Daniel Bevenius
|
d1e2adba65
llama : set n_outputs to 1 to avoid 0 outputs mean-pooling (#15791)
|
4 months ago |
 Diego Devesa
|
274966226f
llama : fix fattn reserve call n_seqs parameter (#15699)
|
4 months ago |
|
Diego Devesa
|
9777032dcc
llama : separate compute buffer reserve from fattn check (#15696)
|
4 months ago |
 Johannes Gäßler
|
e81b8e4b7f
llama: use FA + max. GPU layers by default (#15434)
|
4 months ago |
|
Georgi Gerganov
|
8a4280ce43
kv-cache : remove LLAMA_SET_ROWS checks (#15505)
|
5 months ago |
|
Georgi Gerganov
|
85cc1ae998
context : print graph stats for memory-less contexts (#15586)
|
5 months ago |
|
Georgi Gerganov
|
9ebebef62f
llama : remove KV cache defragmentation logic (#15473)
|
5 months ago |
|
Georgi Gerganov
|
cd36b5e5c7
llama : remove deprecated llama_kv_self API (#15472)
|
5 months ago |
|
Georgi Gerganov
|
715a6db02c
kv-cache : drop the "unified" prefix (#15467)
|
5 months ago |
|
Georgi Gerganov
|
9d262f4bad
server : remove swa_full warning (#15399)
|
5 months ago |
|
Georgi Gerganov
|
d32e03f449
server : add SWA checkpoints (#15293)
|
5 months ago |
 Jonathan Graehl
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
5 months ago |
 compilade
|
ee3a9fcf88
context : fix index overflow on huge outputs (#15080)
|
5 months ago |
|
Georgi Gerganov
|
a4569c41fd
llama : enable LLAMA_SET_ROWS=1 by default (#14959)
|
5 months ago |
|
Georgi Gerganov
|
ba42794c9e
graph : fix equal_seq() check (#14986)
|
5 months ago |
|
Daniel Bevenius
|
ca0ef2dddb
llama : clarify comment about pp and tg graphs [no ci] (#14895)
|
6 months ago |
|
Georgi Gerganov
|
c1dbea752a
context : restore preemptive sched reset when LLAMA_SET_ROWS=0 (#14870)
|
6 months ago |
|
Georgi Gerganov
|
e4868d16d2
context : perform output reorder lazily upon access after sync (#14853)
|
6 months ago |
|
Georgi Gerganov
|
d498af3d5a
graph : avoid huge warm-up graphs for MoE models (#14753)
|
6 months ago |
|
Georgi Gerganov
|
8f974bc1e9
graph : refactor context to not pass gf explicitly (#14629)
|
6 months ago |
|
Georgi Gerganov
|
01612b7409
llama : reuse compute graphs (#14482)
|
6 months ago |
|
Georgi Gerganov
|
225e7a1438
llama : add high-throughput mode (#14363)
|
6 months ago |
 Aman Gupta
|
9c9e4fc635
llama-context: add ability to get logits (#14672)
|
6 months ago |
|
Georgi Gerganov
|
7b50d589a8
kv-cells : fix tracking of seq_pos (#14339)
|
7 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 |
|
Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
7 months ago |
|
Georgi Gerganov
|
c311ac664d
cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)
|
7 months ago |
|
Georgi Gerganov
|
b9912ac570
batch : auto-gen positions + verify multi-sequence input (#14177)
|
7 months ago |
