Issues 共 391
Bug: lalmafile save queries to file even --disable-log is specified
#966 · licaonkter · 2026-05-14
Bug: No usable GPU found, --gpu-layers option will be ignored but AMD GPU does exist
#965 · ghost · 2026-05-14
Bug: can't detect graphics card
#957 · Leonard-Li777 · 2026-05-03
Bug: 0.10.0 release breaks GPU on older OSs
#942 · yjftsjthsd-g · 2026-04-10
Bug: Vulkan support on Windows does not work consistently
#938 · aittalam · 2026-04-08
How to pass llama-server cli options?
#936 · devingfx · 2026-04-07
Improve Vulkan dylib speed
#931 · aittalam · 2026-03-31
Bug: llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35'
#910 · toohamster · 2026-03-14
Bug: Qwen3-0.6B-Q5_K_S.llamafile: DOS/MBR boot sector; partition 1 : ID=0x7f, active, start-CHS (0x0,0,1), end-CHS (0x3ff,255,63), startsector 0, 4294967295 sectors
#900 · toohamster · 2026-03-04
Bug: template parsing issues with Apertus
#893 · aittalam · 2026-02-25