-
On a Fujifilm X-T2, there is a 100x factor difference between the shutter speed specified and image captured.
````
dave@scorpii ~> gphoto2 --version
gphoto2 2.5.23
Copyright (c) 2000-2019 Mar…
-
Because of this all windows open on the display i cant see and i have to use remote desktop or disable device temporarily to use computer on every startup
windows 11 hdr most recent version
-
### Precheck
* Do a quick search and make sure the issue has not yet been reported *Have seen nothing*
* Do not use the issues tracker for guidance, questions or support (try Elixir Forum, Stack O…
-
### What happened?
OS: Windows
Compiler: `cl` or `clang-cl`
Build command: `cmake .. -GNinja -DCMAKE_C_COMPILER=clang-cl -DCMAKE_CXX_COMPILER=clang-cl -DCMAKE_EXPORT_COMPILE_COMMANDS=1 -DLLAMA_NA…
-
### What happened?
deepseek-v2 model will meet out of memory issue with the kv buffer size allocating about 43G with a 160K context length from the model. But when you set the -c or --ctx_size 204…
-
### Summary
Enable CANN support for WASI-NN ggml plugin.
### Details
Adding CANN support to the WASI-NN ggml plugin is relatively straightforward. The main changes involve adding the following code…
-
### What happened?
I am running llama-server like this:
`llama-server -c 102400 -ngl 100 -m Replete-LLM-V2.5-Qwen-14b-IQ3_M.gguf --chat-template chatml --check-tensors -ctk q8_0 -ctv q8_0 -fa --pa…
-
Traceback (most recent call last):
File "/usr/bin/ebook-meta", line 21, in
sys.exit(main())
^^^^^^
File "/usr/lib/calibre/calibre/ebooks/metadata/cli.py", line 220, in main
…
-
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python==0.1.78 Normal Compilation
Unable to compile after AMDGPU 0.1.78 version
-
# Prerequisites
Following the instructions in the README, Linux Ubuntu Focal
rm -rf build; mkdir build; cd buil
cmake -DLLAMA_CUBLAS=1 ..
cmake --build . --config Release
# Expected Behavior
…