 Georgi Gerganov
|
3d1cf3cf33
sync : ggml
|
hai 11 meses |
 cmdr2
|
0cbee131ad
cuda/vulkan: specify fp32-only support for some operations in supports_op (ggml/1129)
|
hai 11 meses |
|
Georgi Gerganov
|
8371d44595
sync : ggml
|
hai 11 meses |
|
cmdr2
|
87abb7e903
cuda/cpu: Increase support for fp16 unary operations (ggml/1125)
|
hai 11 meses |
 Diego Devesa
|
6d4c23b81b
whisper : support GGML_BACKEND_DL (whisper/2843)
|
hai 11 meses |
 midnight
|
6512a90037
cmake : fix compile assumptions for power9/etc (whisper/2777)
|
hai 11 meses |
 petterreinholdtsen
|
4512055792
Told cmake to install ggml-cpp.h as a public header file. (ggml/1126)
|
hai 11 meses |
 cmdr2
|
f54a4ba11e
Support pure float16 add/sub/mul/div operations in the CUDA (and CPU) backend (ggml/1121)
|
hai 11 meses |
|
Georgi Gerganov
|
aede2074f6
scripts : sync-ggml-am.sh fix
|
hai 11 meses |
 Daniel Bevenius
|
2679c3b55d
ci : set GITHUB_ACTION env var for server tests (#12162)
|
hai 11 meses |
 dm4
|
c43af9276b
tts: add speaker file support (#12048)
|
hai 11 meses |
|
Diego Devesa
|
d5c63cd7f9
test-backend-ops : add option -p to filter by op params (#12155)
|
hai 11 meses |
 ag2s20150909
|
9660ffef58
ggml : fix kleidiai build (#12159)
|
hai 11 meses |
 Eric Curtin
|
c950a1f692
Adding UTF-8 support to llama.cpp (#12111)
|
hai 11 meses |
 Xuan-Son Nguyen
|
7b69003af7
webui : add ?m=... and ?q=... params (#12148)
|
hai 11 meses |
 Akarshan Biswas
|
ece9745bb8
SYCL: Move CPY kernels to a separate file and add few missing kernels (#12133)
|
hai 11 meses |
|
Diego Devesa
|
cc473cac7c
ggml-backend : keep paths in native string type when possible (#12144)
|
hai 11 meses |
 Sigbjørn Skjæret
|
14dec0c2f2
main: use jinja chat template system prompt by default (#12118)
|
hai 11 meses |
|
Sigbjørn Skjæret
|
1782cdfed6
main: update outdated system prompt message (followup to #12131) (#12132)
|
hai 11 meses |
|
Sigbjørn Skjæret
|
45a8e76745
common : add --system-prompt parameter, replace behavior of -p in conversation mode (#12131)
|
hai 11 meses |
 Erik Scholz
|
80c41ddd8f
CUDA: compress mode option and default to size (#12029)
|
hai 11 meses |
 Vivian
|
2cc4a5e44a
webui : minor typo fixes (#12116)
|
hai 11 meses |
|
Xuan-Son Nguyen
|
06c2b1561d
convert : fix Norway problem when parsing YAML (#12114)
|
hai 11 meses |
 William Tambellini
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
hai 11 meses |
|
Xuan-Son Nguyen
|
c43a3e7996
llama : add Phi-4-mini support (supersede #12099) (#12108)
|
hai 11 meses |
 Alex Brooks
|
84d5f4bc19
Update granite vision docs for 3.2 model (#12105)
|
hai 11 meses |
 Rémy O
|
438a83926a
vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (#11595)
|
hai 11 meses |
 Johannes Gäßler
|
9c42b1718c
CUDA: fix logic for V100 + GGML_CUDA_FORCE_MMQ (#12098)
|
hai 11 meses |
 Prashant Vithule
|
05e6f5aad0
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064)
|
hai 11 meses |
 hipudding
|
673cfef9aa
CANN: Fix build error with GCC 13 (#11990)
|
hai 11 meses |
