 Georgi Gerganov
|
d408bb9268
clip : disable GPU support (#10896)
|
1 anno fa |
|
Georgi Gerganov
|
0bf2d10c55
tts : add OuteTTS support (#10784)
|
1 anno fa |
 HimariO
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 anno fa |
 piDack
|
01e6d9bb71
clip : add sycl support (#10574)
|
1 anno fa |
 Ting Lou
|
678d7994f4
llava: return false instead of exit (#10546)
|
1 anno fa |
 Diego Devesa
|
9f40989351
ggml : move CPU backend to a separate file (#10144)
|
1 anno fa |
|
Georgi Gerganov
|
cad341d889
metal : reduce command encoding overhead (#9698)
|
1 anno fa |
|
Georgi Gerganov
|
6262d13e0b
common : reimplement logging (#9418)
|
1 anno fa |
|
Georgi Gerganov
|
d6a04f872d
ggml : hide ggml_object, ggml_cgraph, ggml_hash_set (#9408)
|
1 anno fa |
 tc-mb
|
7ea8d80d53
llava : the function "clip" should be int (#9237)
|
1 anno fa |
 Justine Tunney
|
436787f170
llama : fix time complexity of string replacement (#9163)
|
1 anno fa |
 fairydreaming
|
f63f603c87
llava : zero-initialize clip_ctx structure fields with aggregate initialization 908)
|
1 anno fa |
 Changyeon Kim
|
2f3c1466ff
llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model. (#8984)
|
1 anno fa |
|
tc-mb
|
d565bb2fd5
llava : support MiniCPM-V-2.6 (#8967)
|
1 anno fa |
|
Georgi Gerganov
|
45a55b91aa
llama : better replace_all (cont) (#8926)
|
1 anno fa |
|
tc-mb
|
3071c0a5f2
llava : support MiniCPM-V-2.5 (#7599)
|
1 anno fa |
|
slaren
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
1 anno fa |
 hipudding
|
1bdd8ae19f
[CANN] Add Ascend NPU backend (#6035)
|
1 anno fa |
 Daniel Bevenius
|
9b31a40c6d
clip : suppress unused variable warnings (#8105)
|
1 anno fa |
 Andrei
|
d11afd6652
llava : fix moondream support (#7163)
|
1 anno fa |
|
Georgi Gerganov
|
9da243b36a
Revert "llava : add support for moondream vision language model (#6899)"
|
1 anno fa |
 vik
|
46e12c4692
llava : add support for moondream vision language model (#6899)
|
1 anno fa |
|
Daniel Bevenius
|
4ab99d8d47
clip : rename lerp function to avoid conflict (#6894)
|
1 anno fa |
|
Justine Tunney
|
89b0bf0d5d
llava : use logger in llava-cli (#6797)
|
1 anno fa |
 Ziang Wu
|
66ba560256
llava : fix MobileVLM (#6364)
|
1 anno fa |
|
slaren
|
280345968d
cuda : rename build flag to LLAMA_CUDA (#6299)
|
1 anno fa |
|
Ziang Wu
|
272935b281
llava : add MobileVLM_V2 backup (#6175)
|
1 anno fa |
|
Georgi Gerganov
|
d795988d9e
Revert "llava : add a MobileVLM_V2-1.7B backup (#6152)"
|
1 anno fa |
|
Ziang Wu
|
f8c4e745e1
llava : add a MobileVLM_V2-1.7B backup (#6152)
|
1 anno fa |
 Felix
|
104f5e0fc1
clip : fix memory leak (#6138)
|
1 anno fa |
