Daniel Bevenius
|
a057897ad4
llama : add xcframework build script (#11996)
|
10 mesi fa |
mgroeber9110
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
10 mesi fa |
Georgi Gerganov
|
20a9b8f5e1
readme : fix roadmap link (#12185)
|
10 mesi fa |
Sigbjørn Skjæret
|
56d7a9f812
main: allow preloading conversation with -p and add -st / --single-turn (#12145)
|
10 mesi fa |
Olivier Chafik
|
1a24c4621f
`server`: fix deadly typo in response_format.json_schema.schema handling (#12168)
|
10 mesi fa |
David Huang
|
becade5de7
HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (#12032)
|
10 mesi fa |
Georgi Gerganov
|
dfd6b2c0be
sync : ggml
|
10 mesi fa |
cmdr2
|
b64d7cc272
cuda: unary ops as float + de-duplicate (ggml/1130)
|
10 mesi fa |
Georgi Gerganov
|
3d1cf3cf33
sync : ggml
|
10 mesi fa |
cmdr2
|
0cbee131ad
cuda/vulkan: specify fp32-only support for some operations in supports_op (ggml/1129)
|
10 mesi fa |
Georgi Gerganov
|
8371d44595
sync : ggml
|
10 mesi fa |
cmdr2
|
87abb7e903
cuda/cpu: Increase support for fp16 unary operations (ggml/1125)
|
10 mesi fa |
Diego Devesa
|
6d4c23b81b
whisper : support GGML_BACKEND_DL (whisper/2843)
|
10 mesi fa |
midnight
|
6512a90037
cmake : fix compile assumptions for power9/etc (whisper/2777)
|
11 mesi fa |
petterreinholdtsen
|
4512055792
Told cmake to install ggml-cpp.h as a public header file. (ggml/1126)
|
10 mesi fa |
cmdr2
|
f54a4ba11e
Support pure float16 add/sub/mul/div operations in the CUDA (and CPU) backend (ggml/1121)
|
10 mesi fa |
Georgi Gerganov
|
aede2074f6
scripts : sync-ggml-am.sh fix
|
10 mesi fa |
Daniel Bevenius
|
2679c3b55d
ci : set GITHUB_ACTION env var for server tests (#12162)
|
10 mesi fa |
dm4
|
c43af9276b
tts: add speaker file support (#12048)
|
10 mesi fa |
Diego Devesa
|
d5c63cd7f9
test-backend-ops : add option -p to filter by op params (#12155)
|
10 mesi fa |
ag2s20150909
|
9660ffef58
ggml : fix kleidiai build (#12159)
|
10 mesi fa |
Eric Curtin
|
c950a1f692
Adding UTF-8 support to llama.cpp (#12111)
|
10 mesi fa |
Xuan-Son Nguyen
|
7b69003af7
webui : add ?m=... and ?q=... params (#12148)
|
10 mesi fa |
Akarshan Biswas
|
ece9745bb8
SYCL: Move CPY kernels to a separate file and add few missing kernels (#12133)
|
10 mesi fa |
Diego Devesa
|
cc473cac7c
ggml-backend : keep paths in native string type when possible (#12144)
|
10 mesi fa |
Sigbjørn Skjæret
|
14dec0c2f2
main: use jinja chat template system prompt by default (#12118)
|
10 mesi fa |
Sigbjørn Skjæret
|
1782cdfed6
main: update outdated system prompt message (followup to #12131) (#12132)
|
10 mesi fa |
Sigbjørn Skjæret
|
45a8e76745
common : add --system-prompt parameter, replace behavior of -p in conversation mode (#12131)
|
10 mesi fa |
Erik Scholz
|
80c41ddd8f
CUDA: compress mode option and default to size (#12029)
|
10 mesi fa |
Vivian
|
2cc4a5e44a
webui : minor typo fixes (#12116)
|
10 mesi fa |