 Georgi Gerganov
|
0bf16de07b
contributing : add note about write access
|
1 year ago |
 Molly Sophia
|
2d5dd7bb3f
ggml : add epsilon as a parameter for group_norm (#8818)
|
1 year ago |
 Douglas Hanley
|
cdd1889de6
convert : add support for XLMRoberta embedding models (#8658)
|
1 year ago |
 Mengqing Cao
|
c21a896405
[CANN]: Fix ggml_backend_cann_buffer_get_tensor (#8871)
|
1 year ago |
 Neo Zhang
|
d4ff847153
[SYCL] correct cmd name (#8877)
|
1 year ago |
 Liu Jia
|
0a4ce78681
common : Changed tuple to struct (TODO fix) (#8823)
|
1 year ago |
 wangshuai09
|
bc0f887e15
cann: fix buffer_num and runtime speed slowly error (#8865)
|
1 year ago |
 Eric Curtin
|
b42978e7e4
readme : add ramalama to the availables UI (#8811)
|
1 year ago |
 Justine Tunney
|
b9dfc25ca3
ggml : fix overflows in elu function (#8866)
|
1 year ago |
 Brian
|
1ef14b3007
py: Add more authorship metadata from model card (#8810)
|
1 year ago |
 fairydreaming
|
d3f0c7166a
Stop the generation when <|eom_id|> token is encountered - needed for Llama 3.1 tool call support (#8858)
|
1 year ago |
 stduhpf
|
e31a4f6797
cmake: fix paths for vulkan shaders compilation on Windows (#8573)
|
1 year ago |
 BarfingLemurs
|
400ae6f65f
readme : update model list (#8851)
|
1 year ago |
|
Georgi Gerganov
|
f1ea5146d7
llama : better replace_all (#8852)
|
1 year ago |
 0cc4m
|
064cdc265f
vulkan : fix Qantized Mat-Vec Mul on AMD GPUs for ncols < 64 (#8855)
|
1 year ago |
|
Georgi Gerganov
|
5587e57a76
sync : ggml
|
1 year ago |
|
0cc4m
|
a3738b2fa7
vulkan : implement Stable Diffusion operators (ggml/904)
|
1 year ago |
 Daniel Bevenius
|
655858ace0
ggml : move c parameter comment to ggml_rope_ext (ggml/901)
|
1 year ago |
|
wangshuai09
|
c02b0a8a4d
cann: support q4_0 model (#8822)
|
1 year ago |
 Brandon Squizzato
|
0d6fb52be0
Install curl in runtime layer (#8693)
|
1 year ago |
 ardfork
|
978ba3d83d
Server: Don't ignore llama.cpp params (#8754)
|
1 year ago |
 Brian Cunnie
|
ecf6b7f23e
batched-bench : handle empty `-npl` (#8839)
|
1 year ago |
|
Daniel Bevenius
|
01aae2b497
baby-llama : remove duplicate vector include
|
1 year ago |
|
Georgi Gerganov
|
4b77ea95f5
flake.lock: Update (#8847)
|
1 year ago |
 jdomke
|
76614f352e
ggml : reading the runtime sve config of the cpu (#8709)
|
1 year ago |
 Sigbjørn Skjæret
|
b72c20b85c
Fix conversion of unnormalized BF16->BF16 weights (#7843)
|
1 year ago |
|
Mengqing Cao
|
e09a800f9a
cann: Fix ggml_cann_im2col for 1D im2col (#8819)
|
1 year ago |
 Ouadie EL FAROUKI
|
0fbbd88458
[SYCL] Fixing wrong VDR iq4nl value (#8812)
|
1 year ago |
 matteo
|
afbb4c1322
ggml-cuda: Adding support for unified memory (#8035)
|
1 year ago |
 Alex O'Connell
|
b7a08fd5e0
Build: Only include execinfo.h on linux systems that support it (#8783)
|
1 year ago |
