 Daniel Bevenius
|
a91d035b90
ci : revert back to macos-13 for macOS-latest-cmake-x64 (#16040)
|
hai 4 meses |
 Jie Fu (傅杰)
|
745cbcf2fe
llama-quant : fix the verification of attention layers for encoder-decoder models (#16023)
|
hai 4 meses |
|
Jie Fu (傅杰)
|
1cbd80f8cf
examples : support encoder-decoder models in the simple example (#16002)
|
hai 4 meses |
 Shane A
|
85286f3548
model : add OLMo3 support (#16015)
|
hai 4 meses |
 Chenguang Li
|
d5fabe3682
CANN: Optimize ggml_cann_set_device (#15935)
|
hai 4 meses |
 jacekpoplawski
|
8ff206097c
llama-bench: add --n-cpu-moe support (#15952)
|
hai 4 meses |
|
Daniel Bevenius
|
77475530b8
ci : use macos-latest for arm64 webgpu build (#16029)
|
hai 4 meses |
|
Daniel Bevenius
|
3913f8730e
ggml : fix padding in timestep embedding kernels (#15932)
|
hai 4 meses |
|
Daniel Bevenius
|
76888d202e
ci : upload xcframework artifact from ios-xcode-build job (#16010)
|
hai 4 meses |
 Bowen Han
|
f1fbffb5c0
fix: apply clang-format to CUDA macros (#16017)
|
hai 4 meses |
|
Daniel Bevenius
|
51abc96bdc
ci : update macos-latest* jobs to use macos-latest (#15938)
|
hai 4 meses |
 Yuri Khrustalev
|
07808ebb07
cmake : Do not install tools on iOS targets (#15903)
|
hai 4 meses |
 Aman Gupta
|
6d758839ff
Add LLaDA-7b-MoE diffusion model (#16003)
|
hai 4 meses |
 Jake Karnes
|
3d4053f77f
CUDA: fix im2col_3d to respect non-contiguous inputs (views) (#15956)
|
hai 4 meses |
 Diego Devesa
|
dc381aa9a6
docker : enable rocWMMA in ROCm images, add gfx1151 (#15997)
|
hai 4 meses |
|
Diego Devesa
|
10d197409b
releases : switch to rocWMMA develop branch, add gfx1151 (#15992)
|
hai 4 meses |
 yael-works
|
b907255f4b
SYCL: Add COUNT_EQUAL operator support (#15991)
|
hai 4 meses |
 Nikolay Popov
|
28c39da7c6
llama-run: Fix model download on Windows (#15988)
|
hai 4 meses |
|
Aman Gupta
|
106220562a
CUDA: some micro-optimizations in mmf.cuh for mul_mat_id (#15926)
|
hai 4 meses |
 ddh0
|
a68f31edd7
fix KLD percentile output (#15999)
|
hai 4 meses |
 Sigbjørn Skjæret
|
b8e09f08b9
model : add grok-2 support (#15539)
|
hai 4 meses |
|
Sigbjørn Skjæret
|
6c019cb04e
server : only attempt to enable thinking if using jinja (#15967)
|
hai 4 meses |
 Georgi Gerganov
|
9dcd200d57
metal : remove memory pools (#15966)
|
hai 4 meses |
 Adam
|
0fa154e350
rocm.Dockerfile: added gfx1200,gfx1201 architectures to support AMD Radeon RX 9000 series (#15994)
|
hai 4 meses |
 Ruben Ortlam
|
261e6a20ff
Vulkan: Clean up mul_mm shader (#15987)
|
hai 4 meses |
 lcy
|
a0e13dcbe5
build: fix the build failures of Windows HIP release job (#15984)
|
hai 4 meses |
|
Georgi Gerganov
|
a14bd35014
metal : fix kernel requirements (#15983)
|
hai 4 meses |
 Radoslav Gerganov
|
918b26f197
rpc : fix regression when --device is used (#15981)
|
hai 4 meses |
|
Diego Devesa
|
9ecb884346
releases : update ROCM, add gfx1200, gfx1201, gfx1151 (#15972)
|
hai 4 meses |
|
Radoslav Gerganov
|
d1c6f11f47
doc : update documentation for --tensor-split (#15980)
|
hai 4 meses |
