Chenguang Li
|
bbd57b7eaf
CANN: GGML_OP_CPY optimization (#15070)
|
6 months ago |
hipudding
|
be48528b06
CANN: Add broadcast for softmax and FA (#15208)
|
6 months ago |
Chenguang Li
|
2241453252
CANN: add support for ACL Graph (#15065)
|
6 months ago |
Georgi Gerganov
|
fd1234cb46
llama : add gpt-oss (#15091)
|
6 months ago |
diannao
|
2860d479b4
docker : add cann build pipline (#14591)
|
6 months ago |
hipudding
|
11490b3672
CANN: Improve loading efficiency after converting weights to NZ format. (#14985)
|
6 months ago |
hipudding
|
204f2cf168
CANN: Add ggml_set_rows (#14943)
|
6 months ago |
hipudding
|
11dd5a44eb
CANN: Implement GLU ops (#14884)
|
6 months ago |
chen fan
|
14c28dfc50
CANN: weight format to NZ for Ascend310P3 (#14407)
|
6 months ago |
Georgi Gerganov
|
05fec5bd29
ggml : add build-time message to remind about ggml_set_rows (#14661)
|
7 months ago |
Xuan-Son Nguyen
|
98bab638fb
ggml : add ggml_scale_bias (#14417)
|
7 months ago |
Georgi Gerganov
|
a70c8a0c4b
kv-cache : use ggml_set_rows (#14285)
|
7 months ago |
Georgi Gerganov
|
ec68e84c32
ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435)
|
7 months ago |
Xinpeng Dou
|
e21d2d4ae2
CANN: Simplify the environment variable setting(#13104)
|
8 months ago |
Bizhao Shi
|
2d38b6e400
CANN: Add the basic supports of Flash Attention kernel (#13627)
|
8 months ago |
Chenguang Li
|
faaaff5f94
CANN: Support MUL_MAT_ID for q8_0 and q4_0 (#13705)
|
8 months ago |
Chenguang Li
|
33d7aed4a8
CANN: Support MOE Model MUL_MAT_ID (#13042)
|
8 months ago |
hipudding
|
7a395f67a7
CANN: Add support for async operator submission (#12864)
|
9 months ago |
Chenguang Li
|
b43d89e311
CANN: Add 310P operator support check (#12962)
|
10 months ago |
hipudding
|
54a7272043
CANN: Add x86 build ci (#12950)
|
10 months ago |
Chenguang Li
|
0019279bb5
CANN: Opt ROPE optimization (#12865)
|
10 months ago |
Xinpeng Dou
|
b0c75ac9f9
CANN: Optimize CANN buffer pool memory management (#12875)
|
10 months ago |
Diego Devesa
|
fe92821ea9
ggml : add bilinear upscale support (ggml/1185)
|
10 months ago |
Chenguang Li
|
fe5b78c896
CANN: Support more ops (#12841)
|
10 months ago |
Chenguang Li
|
6e1c4cebdb
CANN: Support Opt CONV_TRANSPOSE_1D and ELU (#12786)
|
10 months ago |
zhouwg
|
52b3d71f12
CANN: fix typo in ggml-cann (#12733)
|
10 months ago |
hipudding
|
d0d5b2232b
CANN: Refactor to reduce duplicate code (#12731)
|
10 months ago |
Chenguang Li
|
65cfe136a0
CANN: Support operator SIN COS ARGMAX (#12709)
|
10 months ago |
hipudding
|
2a0dc97e56
CANN: Fix failed test cases (#12708)
|
10 months ago |
Chenguang Li
|
9bacd6b374
[CANN] get_rows and dup optimization (#12671)
|
10 months ago |