| .. |
|
android
|
52fc7fee8a
android: fix missing screenshots for Android.md (#18156)
|
hace 4 semanas |
|
backend
|
ce734a8a2f
ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)
|
hace 4 semanas |
|
development
|
7f2b2f3c77
arch: refactor LLM_TENSOR_NAMES (#18051)
|
hace 1 mes |
|
multimodal
|
c4e9239064
model : support MiniCPM-V 4.5 (#15575)
|
hace 4 meses |
|
ops
|
4aced7a631
[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4, swiglu_oai (#17826)
|
hace 1 mes |
|
android.md
|
52fc7fee8a
android: fix missing screenshots for Android.md (#18156)
|
hace 4 semanas |
|
build-riscv64-spacemit.md
|
79d61896d3
ggml-cpu: add ggml_thread_cpu_relax with Zihintpause support (#17784)
|
hace 1 mes |
|
build-s390x.md
|
40be51152d
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free (#15839)
|
hace 4 meses |
|
build.md
|
017761daf5
ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690)
|
hace 1 mes |
|
docker.md
|
fb644247de
CLI: fixed adding cli and completion into docker containers, improved docs (#18003)
|
hace 1 mes |
|
function-calling.md
|
792b44f2ed
server : add documentation for `parallel_tool_calls` param (#15647)
|
hace 4 meses |
|
install.md
|
ea1431b0fa
docs : add "Quick start" section for new users (#13862)
|
hace 7 meses |
|
llguidance.md
|
89daa2564f
llguidance build fixes for Windows (#11664)
|
hace 11 meses |
|
multimodal.md
|
00fa15fedc
mtmd : add support for Voxtral (#14862)
|
hace 5 meses |
|
ops.md
|
4aced7a631
[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4, swiglu_oai (#17826)
|
hace 1 mes |
Alfred
ce734a8a2f
ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)