 Aleksander Grygier
|
2a9b63383a
Improve code block color theming (#16325)
|
hace 3 meses |
 Sigbjørn Skjæret
|
1104ca1a1c
ci : use registry cache for docker builds (#16366)
|
hace 3 meses |
|
Aleksander Grygier
|
4f1575921c
Add optional setting for showing "Model used:" information (#16337)
|
hace 3 meses |
 Eve
|
132d673554
vulkan: make ggml_vk_default_dispatcher support older vulkan headers (#16345)
|
hace 3 meses |
|
Aleksander Grygier
|
aa9538a63a
webui: Remove running `llama-server` within WebUI `dev.sh` script (#16363)
|
hace 3 meses |
 Bartowski
|
e74c92e842
model : support GLM 4.6 (make a few NextN/MTP tensors not required) (#16359)
|
hace 3 meses |
|
Sigbjørn Skjæret
|
b2ba81dbe0
ci : fix ccache key for ubuntu-cpu-cmake (#16355)
|
hace 3 meses |
 Adrien Gallouët
|
bf6f3b3a19
common : disable progress bar without a tty (#16352)
|
hace 3 meses |
 lhez
|
7c156df414
opencl: support pad_ext (#15888)
|
hace 3 meses |
 Pascal
|
16b0ca0d2e
Chatapi ignore empty sampling (#16330)
|
hace 3 meses |
 Reese Levine
|
8d78cd2613
ggml webgpu: support for rope,div,sub,glu,scale,cont operators (#16187)
|
hace 3 meses |
|
lhez
|
d1c84a662d
opencl: support ne3 in get_rows (#15866)
|
hace 3 meses |
|
Adrien Gallouët
|
364a7a6d4a
common : remove common_has_curl() (#16351)
|
hace 3 meses |
|
Sigbjørn Skjæret
|
2df5bcf357
ci : disable ccache for android (#16348)
|
hace 3 meses |
 Georgi Gerganov
|
075c01567b
ggml : bump version to 0.9.4 (ggml/1363)
|
hace 3 meses |
 anavp-nvidia
|
a014310374
cuda : Enable CUDA Graph usage for Nemotron Nano v2 (NemotronH) (#16328)
|
hace 3 meses |
|
Georgi Gerganov
|
35fb82497e
metal : dynamic simdgroups for MV kernels (#16340)
|
hace 3 meses |
|
Adrien Gallouët
|
3c62aed89f
common : simplify etag tracking by removing json (#16342)
|
hace 3 meses |
 Charles Xu
|
f1eb1cb1eb
kleidiai : fix work size and threads sync for fp16 (#16246)
|
hace 3 meses |
|
lhez
|
de41f2b7bf
codeowners: add codeowners for opencl backend (#16344)
|
hace 3 meses |
 Jeff Bolz
|
a74a0d69f3
tests: override test_set_rows::max_nmse_err to allow for occasional rounding differences (#16295)
|
hace 3 meses |
|
Pascal
|
5f7e166cbf
Fix thinking blocks with quotes + add handling `[THINK]...[/THINK]` blocks (#16326)
|
hace 3 meses |
|
Georgi Gerganov
|
d72f5f7ba2
ci : add AMD runners and workflows (#16249)
|
hace 3 meses |
 alex-spacemit
|
b77e6c18e1
ggml: riscv: add riscv spacemit backend (#15288)
|
hace 3 meses |
|
Georgi Gerganov
|
2ddd3f2356
sync : ggml
|
hace 3 meses |
|
Georgi Gerganov
|
4d3d455d3c
sync : whisper.cpp (ggml/1359)
|
hace 3 meses |
 Daniel Bevenius
|
c9b1c06467
ggml : remove -dev suffix from release version (ggml/1355)
|
hace 3 meses |
|
Daniel Bevenius
|
b6ae75afb4
ggml : bump version to 0.9.3 (ggml/1353)
|
hace 3 meses |
|
Georgi Gerganov
|
b6dff20e2f
ggml : prepare for development of 0.9.2-dev
|
hace 4 meses |
|
Georgi Gerganov
|
2db78c75e4
ggml : bump version to 0.9.1
|
hace 4 meses |
