 Aaron Teo
|
50d2227953
ggml-cpu: reduce asm calls for hsum (#14037)
|
hace 7 meses |
|
Aaron Teo
|
6231c5cd6d
ggml-cpu: fix uncaught underscore terminators (#14023)
|
hace 7 meses |
 Charles Xu
|
ef035803eb
ggml: Add Apple support for GGML_CPU_ALL_VARIANTS (#14258)
|
hace 7 meses |
 Xuan-Son Nguyen
|
413977de32
mtmd : refactor llava-uhd preprocessing logic (#14247)
|
hace 7 meses |
|
Xuan-Son Nguyen
|
95402553a5
llama-chat : fix multiple system message for gemma, orion (#14246)
|
hace 7 meses |
 Sigbjørn Skjæret
|
3865cff4f5
convert : fix null head_dim AutoConfig regression (#14248)
|
hace 7 meses |
 Georgi Gerganov
|
d03172cc79
sync : ggml
|
hace 7 meses |
 Daniel Bevenius
|
dd8e59f443
ggml : disable warnings for tests when using MSVC (ggml/1273)
|
hace 7 meses |
|
Daniel Bevenius
|
bbe98d2784
ggml : remove unused ggml_context_container (ggml/1272)
|
hace 7 meses |
|
Daniel Bevenius
|
c2056ed6d4
examples : include examples in msvc disable warn (ggml/1270)
|
hace 7 meses |
 bandoti
|
c46503014d
cmake: remove shader-gen step-targets from ggml-vulkan (#14226)
|
hace 7 meses |
 xctan
|
860a9e4eef
ggml-cpu : remove the weak alias trick (#14221)
|
hace 7 meses |
 R0CKSTAR
|
fe9d60e74a
musa: fix build warning (unused variable) (#14231)
|
hace 7 meses |
|
Sigbjørn Skjæret
|
e434e69183
common : suggest --jinja when autodetection fails (#14222)
|
hace 7 meses |
|
Georgi Gerganov
|
89fea80d29
server : fix incorrect usage of llama_get_embeddings() (#14225)
|
hace 7 meses |
 Diego Devesa
|
6adc3c3ebc
llama : add thread safety test (#14035)
|
hace 7 meses |
|
bandoti
|
0dbcabde8c
cmake: clean up external project logic for vulkan-shaders-gen (#14179)
|
hace 7 meses |
 Đinh Trọng Huy
|
ad590be98c
model : add NeoBERT (#14164)
|
hace 7 meses |
 uvos
|
7d6d91babf
HIP: disable rocwmma on gfx12 by default until rocm 7.0 (#14202)
|
hace 7 meses |
|
Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
hace 7 meses |
|
Charles Xu
|
3ba0d843c6
ggml: Add Android support for GGML_CPU_ALL_VARIANTS (#14206)
|
hace 7 meses |
 Bartowski
|
0bf49eb668
convert : remove arcee change in convert_hf_to_gguf_update.py (#14207)
|
hace 7 meses |
|
Đinh Trọng Huy
|
4ad243677b
gguf-py : allow key override when adding value to GGUFWriter (#14194)
|
hace 7 meses |
 Jeff Bolz
|
c89c2d1ab9
vulkan: mutex around vkQueueSubmit (#14127)
|
hace 7 meses |
|
xctan
|
3555b3004b
ggml-cpu : rework weak alias on apple targets (#14146)
|
hace 7 meses |
|
Bartowski
|
d7da8dc83a
model : Add support for Arcee AI's upcoming AFM model (#14185)
|
hace 7 meses |
 Eric Curtin
|
cd355eda7d
server : When listening on a unix domain socket don't print http:// and port (#14180)
|
hace 7 meses |
 Ed Addario
|
30e5b01de2
quantize : change int to unsigned int for KV overrides (#14197)
|
hace 7 meses |
|
uvos
|
e54b394082
CUDA/HIP: fix ssm_scan on devices where warp size is not 32 (#14196)
|
hace 7 meses |
|
uvos
|
2c2caa4443
HIP: Replace usage of depricated preprocessor macro __AMDGCN_WAVEFRONT_SIZE__ (#14183)
|
hace 7 meses |
