Closed
Description
Name and Version
./llama-cli --version
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon Graphics (RADV RENOIR) (radv) | uma: 1 | fp16: 1 | warp size: 64 | shared memory: 65536 | matrix cores: none
version: 4882 (be7c303)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
llama-cli (Vulkan Linux x86 build)
Command line
./llama-cli -hf <any model>
common_get_hf_file: llama.cpp built without libcurl, downloading from Hugging Face not supported.
Problem description & steps to reproduce
I extracted llama-b4882-bin-ubuntu-vulkan-x64.zip and was unable to download models from Hugging Face due to missing curl support. Could you please build future packages with libcurl support ?
./llama-cli -hf
common_get_hf_file: llama.cpp built without libcurl, downloading from Hugging Face not supported.
Workaround:
Install llama-b4914-bin-ubuntu-x64.zip which includes libcurl support.