 Diego Devesa
|
d5c63cd7f9
test-backend-ops : add option -p to filter by op params (#12155)
|
10 months ago |
 ag2s20150909
|
9660ffef58
ggml : fix kleidiai build (#12159)
|
10 months ago |
 Eric Curtin
|
c950a1f692
Adding UTF-8 support to llama.cpp (#12111)
|
10 months ago |
 Xuan-Son Nguyen
|
7b69003af7
webui : add ?m=... and ?q=... params (#12148)
|
10 months ago |
 Akarshan Biswas
|
ece9745bb8
SYCL: Move CPY kernels to a separate file and add few missing kernels (#12133)
|
10 months ago |
|
Diego Devesa
|
cc473cac7c
ggml-backend : keep paths in native string type when possible (#12144)
|
10 months ago |
 Sigbjørn Skjæret
|
14dec0c2f2
main: use jinja chat template system prompt by default (#12118)
|
10 months ago |
|
Sigbjørn Skjæret
|
1782cdfed6
main: update outdated system prompt message (followup to #12131) (#12132)
|
11 months ago |
|
Sigbjørn Skjæret
|
45a8e76745
common : add --system-prompt parameter, replace behavior of -p in conversation mode (#12131)
|
11 months ago |
 Erik Scholz
|
80c41ddd8f
CUDA: compress mode option and default to size (#12029)
|
11 months ago |
 Vivian
|
2cc4a5e44a
webui : minor typo fixes (#12116)
|
11 months ago |
|
Xuan-Son Nguyen
|
06c2b1561d
convert : fix Norway problem when parsing YAML (#12114)
|
11 months ago |
 William Tambellini
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
11 months ago |
|
Xuan-Son Nguyen
|
c43a3e7996
llama : add Phi-4-mini support (supersede #12099) (#12108)
|
11 months ago |
 Alex Brooks
|
84d5f4bc19
Update granite vision docs for 3.2 model (#12105)
|
11 months ago |
 Rémy O
|
438a83926a
vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (#11595)
|
11 months ago |
 Johannes Gäßler
|
9c42b1718c
CUDA: fix logic for V100 + GGML_CUDA_FORCE_MMQ (#12098)
|
11 months ago |
 Prashant Vithule
|
05e6f5aad0
ggml: aarch64: implement SVE kernels for q2_k_q8_k vector dot (#12064)
|
11 months ago |
 hipudding
|
673cfef9aa
CANN: Fix build error with GCC 13 (#11990)
|
11 months ago |
 Eve
|
fbeda9002d
vulkan: matmul dequantization improvements (#12015)
|
11 months ago |
 Daniele
|
581650b7ca
vulkan: improve im2col (#11826)
|
11 months ago |
 Vladimir Vuksanovic
|
b95c8af37c
cmake: Fix ggml backend dependencies and installation (#11818)
|
11 months ago |
 Ting Lou
|
a800ae46da
llava : add struct for FFI bindgen (#12079)
|
11 months ago |
|
Sigbjørn Skjæret
|
69050a11be
Refactor gguf scripts to improve metadata handling (#11909)
|
11 months ago |
 Aleksei Nikiforov
|
3567ee3a94
gguf-py: enable reading non-native endian files (#12081)
|
11 months ago |
 Kante Yin
|
53e4db1012
readme : update infra list (#9096)
|
11 months ago |
 Olivier Chafik
|
d7cfe1ffe0
docs: add docs/function-calling.md to lighten server/README.md's plight (#12069)
|
11 months ago |
 Jeff Bolz
|
a82c9e7c23
vulkan: fix assertion when qy_needs_dequant (#12068)
|
11 months ago |
 rhjdvsgsgks
|
401af80b54
server: handle echo=false on /v1/completions (#12060)
|
11 months ago |
 Judd
|
c132239bfb
add OP sigmoid (#12056)
|
11 months ago |
