Pinned issues
Issues
- 0
User defined operation
#836 opened by Francis235 - 0
issues about YaRN
#835 opened by foldl - 0
Completion of error handling
#834 opened by elfring - 0
ggml how to compute depthwise conv
#833 opened by Francis235 - 0
GGML Fragmentation Issue
#830 opened by zhouwg - 1
`ggml_flip` or `ggml_pad_reflect`?
#819 opened by PABannier - 1
GGML_MAX_NAME is too small.
#825 opened by IntptrMax - 0
Is there interest in `ggml_upscale_to_shape` supporting non integer scaling factors?
#812 opened by balisujohn - 1
- 0
ggml vs onnxruntime on SOC chip
#810 opened by Francis235 - 0
- 0
- 1
Add Qualcomm mobile SoC native backend for GGML
#771 opened by zhouwg - 2
- 5
- 1
Is there interest in implementations of something analogous to `torch.Tensor.scatter_` and `torch.gather`?
#718 opened by balisujohn - 1
- 3
- 0
The library crashes with illegal instructions when the F16C extension isn't supported, please use google's cpu_features library and fail gracefully in such case
#799 opened by yurivict - 2
GGUF quantization meta-data format
#797 opened by mobicham - 2
any support for MUL_MAT operation in unsupported GPU feature? (macos intel/amd gpu)
#796 opened by posojeg - 0
is there any plan to complete the implementation of use supports_op to check if the backend supports the op?
#795 opened by zhouwg - 2
Add dsp backend in ggml.h
#794 opened by zhouwg - 7
Magic number in example
#791 opened by wilderfield - 4
doc: lack of official logo of GGML
#776 opened by zhouwg - 2
Setting tensor's backend
#779 opened by rgerganov - 3
Standardized prompting metadata
#774 opened by MoonRide303 - 0
`test-timestep_embedding` _sometimes_ fails with `ptrace: Operation not permitted.` [opencl-clover, gfx1103] (with `gdb` backtrace.)
#772 opened by dreirund - 0
Quant and Dequant operators
#769 opened by sankalpdayal - 1
- 3
How to deploy my own model using ggml framework
#762 opened by Francis235 - 2
quantization func test failed with GGML_QKK_64
#739 opened by winice-test - 4
Automatically convert pytorch model to ggml
#756 opened by Maknee - 1
Incorrect Error Handling in ggml_backend_graph_compute Function in example/magika/main.cpp
#760 opened by charloco - 1
Replit code completion example not working
#758 opened by hassan404 - 0
Error: Unsupported op TIMESTEP_EMBEDDING
#751 opened by paulocoutinhox - 0
In gpt-2/convert-h5-to-ggml.py : size mismatch for wpe.weight ... torch.Size([50255, 1024]) ...
#745 opened by Twenkid - 0
ggml : add Magika inference
#734 opened by ggerganov - 2
ggml : make ggml_fp16_t private
#720 opened by ggerganov - 0
mnist convert from tensorflow to ggml
#744 opened by datduonguva - 2
ggml : simplify the ggml_compute_forward_ calls
#724 opened by ggerganov - 0
- 0
Does ggml_cont really work?
#735 opened by BayRanger - 2
How do pixel unshuffle in ggml ?
#732 opened by delldu - 2
Division by zero error
#723 opened by cpopescu - 2
ggml : add optional CPU backend context, support reusing threads, async compute
#721 opened by slaren - 0
Error when trying to run GPT inference
#717 opened by thekevinscott - 1
"array size is too large" on model load
#714 opened by iamlemec - 2
- 1
Is a ggml tensor's dimension order reversed?
#710 opened by chunhualiao