Pull Requests ggml-org/ggml

Add Metal support for GGML_OP_DIAG_MASK_INF for CLIP on Apple GPUs

#1395 opened 2025-12-07 22:32 by taradaidv

ggml-cpu: BMI2 is only available on amd64

#1392 opened 2025-11-26 18:15 by candrews

metal: implement cross-entropy and count-equal ops for MNIST

#1390 opened 2025-11-22 07:02 by xi-guo-0

chores : Remove deprecated std::codecvt usage

#1386 opened 2025-11-18 05:55 by AstroAir

metal: accelerated conv2d

#1384 opened 2025-11-11 18:38 by bghira

fix dequant_funcs.comp

#1317 opened 2025-07-29 05:37 by tophyr

ggml-cpu : Add GGML_CPU_FFAST_MATH for sine autovectorization

#1243 opened 2025-05-28 06:26 by danielzgtg

Add support for google-benchmark

#1237 opened 2025-05-23 16:58 by lunochod

Enable UTF-8 Source Encoding for MSVC via CMake

#1226 opened 2025-05-16 09:08 by xiaobing318

Temporary fix for rms norm backward on CPU.

#1197 opened 2025-04-22 21:15 by Alkamist

Review

#1191 opened 2025-04-13 15:00 by xiaopusun

cpu : simd gelu fp32

#1181 opened 2025-04-06 14:55 by CISC

cuda : add missing copyright notice

#1180 opened 2025-04-06 14:44 by CISC

ggml_fp16_t is typedef as uint16_t, there is no need to convert

#1168 opened 2025-03-29 21:00 by nickhuang99

Update example readme/shell output for gpt-2-backend

#1159 opened 2025-03-26 20:59 by rememberlenny

tests: add vulkan configuration in tests

#1115 opened 2025-02-14 02:25 by okamototk

Add an option not to abort on cuda OOM

#1110 opened 2025-02-11 20:43 by WilliamTambellini

ggml : add `ggml_fft` and `ggml_ifft` operator

#1105 opened 2025-02-06 07:36 by ilhamsyahids

ggml-cpu: use lookuptable for ggml op and parallelized some of the memcpy memset etc. calls before ggml_barriers

#1101 opened 2025-02-04 05:20 by Kamayuq

CUDA: update compilation flags for improved performance

#1099 opened 2025-02-03 18:02 by royshil

ggml-cpu: Add bounds checking in `make_block_q4_0x4` function

#1095 opened 2025-02-02 18:50 by ilhamsyahids

GGUF: ggml backend support for writing tensor data

#1033 opened 2024-11-30 10:34 by JohannesGaessler

Update simple-backend.cpp

#1011 opened 2024-11-10 07:57 by paul-tian

Add conv_transpose_1d_gemm

#940 opened 2024-08-28 22:30 by smeso

feat: implement backward computation for more operators

#921 opened 2024-08-12 20:11 by Ronsor

feat: adds new OP ggml_unfold_1d

#867 opened 2024-06-21 20:49 by balisujohn

feat: adds `ggml_pad_ext` to allow prefix padding

#864 opened 2024-06-18 08:42 by balisujohn

[experimental]backend: add new oneDNN backend

#855 opened 2024-06-12 15:44 by rfsaliev

Embed yolo files

#831 opened 2024-05-19 11:32 by katsu560

GGML_CUDA default to ON if CUDA is available.

#817 opened 2024-05-11 09:23 by xth