-
### System Info / 系統信息
ubuntu22.04 python3.11.8
### Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece?
- [ ] docker / docker
- [X] pip install / 通过 pip install 安装
- [ ] installation from …
-
-
Error:
```
/Users/paulo/Developer/workspaces/cpp/ai-kit/vendor/whisper/src/whisper.cpp:2127:23: error: no matching function for call to 'ggml_flash_attn_ext'
cur = ggml_flash_…
-
Trying to compile the program with flash attention enabled errors out
apparently, the ggml_flash_attn() function was replaced by ggml_flash_attn_ext() in ggml in this pr: https://github.com/ggerganov…
-
Please help convert the PyTorch model to a custom GGML binary format.
It would be great for whisper.cpp to support it
-
LoRA is loaded but is not applied. Full logs is attached as file below.
related issue #370
**lora_down|lora_up** [flux_lora.log](https://github.com/user-attachments/files/17118078/flux_lora.log…
-
Build on i386 fails like this:
```
ggml/src/ggml-vulkan.cpp:2626:5: error: no matching function for call to 'vkCmdCopyBuffer'
2626 | vkCmdCopyBuffer(subctx->s->buffer, staging->buffer, dst->bu…
-
warning: not compiled with GPU offload support, --n-gpu-layers option will be ignored
warning: see main README.md for information on enabling GPU BLAS support
Log start
main: build = 2854 (70c312d)…
-
Currently the [ggml](https://github.com/ggerganov/ggml), [llama.cpp](https://github.com/ggerganov/llama.cpp) and [whisper.cpp](https://github.com/ggerganov/whisper.cpp) projects share the same source …
-
I'm receiving and error when attempting to run `glados.py` with 'ggml-common.h not found`. I've noticed that `submodules/whisper.cpp/ggml-common.h` exists though. The script does not exit and the mode…