Georgi Gerganov
|
2776db6c81
Revert "ggml-cpu: handle 3d tensors in repack mat_mul (#17030)" (#17233)
|
vor 2 Monaten |
Diego Devesa
|
879dec341a
ggml-cpu : use template for argsort (#17222)
|
vor 2 Monaten |
TecJesh
|
97d5117217
CANN: Add cross_entropy_loss op support (#16886)
|
vor 2 Monaten |
Aman Gupta
|
a90eb94ca9
CUDA: fuse rope + set_rows (#16884)
|
vor 2 Monaten |
Neo Zhang Jianyu
|
07751f8d44
update SYCL support OPs (#17208)
|
vor 2 Monaten |
o7si
|
ffb6f3d921
vocab : correct bounds check for UGM XCDA array access (#17215)
|
vor 2 Monaten |
Johannes Gäßler
|
5d6838b74f
CUDA: static assert to prevent misuse of memcpy_1 (#17198)
|
vor 2 Monaten |
Mike Abbott
|
92bb442ad9
docker : preserve .so symlinks for docker container builds (#17214)
|
vor 2 Monaten |
Georgi Gerganov
|
374fe09cdd
ggml : use std::sort in ggml_argsort CPU implementation (#17211)
|
vor 2 Monaten |
Aleksander Grygier
|
8e878f0cb4
Update packages + upgrade Storybook to v10 (#17201)
|
vor 2 Monaten |
Xuan-Son Nguyen
|
00c94083b3
server: (refactor) implement generator-based API for task results (#17174)
|
vor 2 Monaten |
Xuan-Son Nguyen
|
017eceed61
ci: add check vendor job (#17179)
|
vor 2 Monaten |
Xuan-Son Nguyen
|
ee8dd5c658
server: move res_error/res_ok to static function (#17167)
|
vor 2 Monaten |
Alberto Cabrera Pérez
|
1c398dc9ec
ggml-cpu: handle 3d tensors in repack mat_mul (#17030)
|
vor 2 Monaten |
Adrien Gallouët
|
52cf111b31
cmake : cleanup (#17199)
|
vor 2 Monaten |
Adrien Gallouët
|
78010a0d52
cmake : move OpenSSL linking to vendor/cpp-httplib (#17177)
|
vor 2 Monaten |
TecJesh
|
655cddd174
CANN: Add L2_NORM op support (#16856)
|
vor 2 Monaten |
Neo Zhang Jianyu
|
5da7664960
[SYCL]fix ci crash about SSM_CONV (#17169)
|
vor 2 Monaten |
Raul Torres
|
23a46ce972
CANN: GGML_CANN_ACL_GRAPH works only USE_ACL_GRAPH enabled (#16861)
|
vor 2 Monaten |
Max Krasnyansky
|
c273d75375
hexagon: various Op fixes (#17135)
|
vor 2 Monaten |
Eve
|
7d019cff74
disable rms norm mul rope for chips with no fp16 rte (#17134)
|
vor 2 Monaten |
sudhiarm
|
3fe36c3238
ci: add Arm-hosted Graviton4 runner (#17021)
|
vor 2 Monaten |
Xuan-Son Nguyen
|
1d45b4228f
vendor: split httplib to cpp/h files (#17150)
|
vor 2 Monaten |
ixgbe
|
ca4844062b
ggml-cpu : add RISC-V RVV (Zvfh) optimization for FP16 to FP32 conversion (#17161)
|
vor 2 Monaten |
duduta
|
73460f6278
ggml-cpu: templateify ggml_compute_forward_rope_f32 and _f16 (#16805)
|
vor 2 Monaten |
Charles Xu
|
8c583242ad
kleidiai: add optimized per-channel kernels for Q8_0 (#16993)
|
vor 2 Monaten |
Mike Abbott
|
4a5b8aff40
cmake : add version to all shared object files (#17091)
|
vor 2 Monaten |
Nicolas B. Pierron
|
d2d626938a
Install rpc-server when GGML_RPC is ON. (#17149)
|
vor 2 Monaten |
levkropp
|
2fc392ce35
convert : register UMT5Model architecture for T5 conversion (#17160)
|
vor 2 Monaten |
lhez
|
ece0f5c177
opencl: add fastdiv and use it in set_rows, ported from cuda (#17090)
|
vor 2 Monaten |