 Daniel Bevenius
|
bbe98d2784
ggml : remove unused ggml_context_container (ggml/1272)
|
7 сар өмнө |
|
Daniel Bevenius
|
c2056ed6d4
examples : include examples in msvc disable warn (ggml/1270)
|
7 сар өмнө |
 bandoti
|
c46503014d
cmake: remove shader-gen step-targets from ggml-vulkan (#14226)
|
7 сар өмнө |
 xctan
|
860a9e4eef
ggml-cpu : remove the weak alias trick (#14221)
|
7 сар өмнө |
 R0CKSTAR
|
fe9d60e74a
musa: fix build warning (unused variable) (#14231)
|
7 сар өмнө |
 Sigbjørn Skjæret
|
e434e69183
common : suggest --jinja when autodetection fails (#14222)
|
7 сар өмнө |
 Georgi Gerganov
|
89fea80d29
server : fix incorrect usage of llama_get_embeddings() (#14225)
|
7 сар өмнө |
 Diego Devesa
|
6adc3c3ebc
llama : add thread safety test (#14035)
|
7 сар өмнө |
|
bandoti
|
0dbcabde8c
cmake: clean up external project logic for vulkan-shaders-gen (#14179)
|
7 сар өмнө |
 Đinh Trọng Huy
|
ad590be98c
model : add NeoBERT (#14164)
|
7 сар өмнө |
 uvos
|
7d6d91babf
HIP: disable rocwmma on gfx12 by default until rocm 7.0 (#14202)
|
7 сар өмнө |
|
Georgi Gerganov
|
d3e64b9f49
llama : rework embeddings logic (#14208)
|
7 сар өмнө |
 Charles Xu
|
3ba0d843c6
ggml: Add Android support for GGML_CPU_ALL_VARIANTS (#14206)
|
7 сар өмнө |
 Bartowski
|
0bf49eb668
convert : remove arcee change in convert_hf_to_gguf_update.py (#14207)
|
7 сар өмнө |
|
Đinh Trọng Huy
|
4ad243677b
gguf-py : allow key override when adding value to GGUFWriter (#14194)
|
7 сар өмнө |
 Jeff Bolz
|
c89c2d1ab9
vulkan: mutex around vkQueueSubmit (#14127)
|
7 сар өмнө |
|
xctan
|
3555b3004b
ggml-cpu : rework weak alias on apple targets (#14146)
|
7 сар өмнө |
|
Bartowski
|
d7da8dc83a
model : Add support for Arcee AI's upcoming AFM model (#14185)
|
7 сар өмнө |
 Eric Curtin
|
cd355eda7d
server : When listening on a unix domain socket don't print http:// and port (#14180)
|
7 сар өмнө |
 Ed Addario
|
30e5b01de2
quantize : change int to unsigned int for KV overrides (#14197)
|
7 сар өмнө |
|
uvos
|
e54b394082
CUDA/HIP: fix ssm_scan on devices where warp size is not 32 (#14196)
|
7 сар өмнө |
|
uvos
|
2c2caa4443
HIP: Replace usage of depricated preprocessor macro __AMDGCN_WAVEFRONT_SIZE__ (#14183)
|
7 сар өмнө |
|
Georgi Gerganov
|
5fce5f948d
kv-cache : fix use-after-move of defrag info (#14189)
|
7 сар өмнө |
 Mikko Juola
|
9ae4143bc6
model : add dots.llm1 architecture support (#14044) (#14118)
|
7 сар өмнө |
|
Georgi Gerganov
|
c311ac664d
cparams : rename LLAMA_MAX_PARALLEL_SEQUENCES to LLAMA_MAX_SEQ (#14188)
|
7 сар өмнө |
|
Georgi Gerganov
|
b9912ac570
batch : auto-gen positions + verify multi-sequence input (#14177)
|
7 сар өмнө |
 Pepijn de Vos
|
00ba772610
docs : remove WIP since PR has been merged (#13912)
|
7 сар өмнө |
 Piotr
|
3cb203c89f
llama-chat : Do not throw when tool parsing fails (#14012)
|
7 сар өмнө |
 Aman Gupta
|
2e42be42bd
compare-llama-bench: add option to plot (#14169)
|
7 сар өмнө |
|
Georgi Gerganov
|
fb85a288d7
vocab : fix build (#14175)
|
7 сар өмнө |
