 Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 年之前 |
|
Georgi Gerganov
|
644fd71b44
sampling : refactor + optimize penalties sampler (#10803)
|
1 年之前 |
 HimariO
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 年之前 |
 kallewoof
|
484d2f31ae
bug-fix: snprintf prints NULL in place of the last character (#10419)
|
1 年之前 |
 Djip007
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 年之前 |
 Riccardo Orlando
|
6fe6247831
llama : add Minerva 7B model support (#10673)
|
1 年之前 |
 JFLFY2255
|
8d0cfd554a
llama: Support MiniCPM-1B (with & w/o longrope) (#10559)
|
1 年之前 |
 Xuan Son Nguyen
|
3b4f2e33e2
llama : add missing LLAMA_API for llama_chat_builtin_templates (#10636)
|
1 年之前 |
|
Xuan Son Nguyen
|
642330ac7c
llama : add enum for built-in chat templates (#10623)
|
1 年之前 |
 Diego Devesa
|
10bce0450f
llama : accept a list of devices to use to offload a model (#10497)
|
1 年之前 |
|
Georgi Gerganov
|
8e752a777b
llama : add check for KV cache shifts (#10401)
|
1 年之前 |
 Johannes Gäßler
|
4e54be0ec6
llama/ex: remove --logdir argument (#10339)
|
1 年之前 |
 Michael Podvitskiy
|
fb4a0ec083
llama : propagate the results of `graph_compute` (#9525)
|
1 年之前 |
|
Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
1 年之前 |
|
Diego Devesa
|
c5b0f4b5d9
llama : refactor model loader with backend registry (#10026)
|
1 年之前 |
|
Georgi Gerganov
|
8d8ff71536
llama : remove Tail-Free sampling (#10071)
|
1 年之前 |
 wwoodsTM
|
ff252ea48e
llama : add DRY sampler (#9702)
|
1 年之前 |
|
Georgi Gerganov
|
55e47786e3
llama : default sampling changes + greedy update (#9897)
|
1 年之前 |
|
Xuan Son Nguyen
|
cda0e4b648
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
|
1 年之前 |
|
Georgi Gerganov
|
99bd4ac28c
llama : infill sampling handle very long tokens (#9924)
|
1 年之前 |
|
Georgi Gerganov
|
755a9b2bf0
llama : add infill sampler (#9896)
|
1 年之前 |
 MaggotHATE
|
fbc98b748e
sampling : add XTC sampler (#9742)
|
1 年之前 |
|
Georgi Gerganov
|
11ac9800af
llama : improve infill support and special token detection (#9798)
|
1 年之前 |
|
Diego Devesa
|
0e9f760eb1
rpc : add backend registry / device interfaces (#9812)
|
1 年之前 |
|
Georgi Gerganov
|
f4d2b8846a
llama : add reranking support (#9510)
|
1 年之前 |
|
Georgi Gerganov
|
739842703e
llama : add comment about thread-safety [no ci] (#9449)
|
1 年之前 |
 nopperl
|
9a913110cf
llama : add support for Chameleon (#8543)
|
1 年之前 |
|
Georgi Gerganov
|
b0f27361f3
sampling : avoid expensive softmax during greedy sampling (#9605)
|
1 年之前 |
|
Michael Podvitskiy
|
37f3a3810e
llama : add llama_n_head() (#9512)
|
1 年之前 |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
1 年之前 |
