mirror of https://github.com/ollama/ollama.git
06b7ee7781
GGML picks the wrong kernel and these systems fail with: Sep 28 22:25:39 xavier ollama[48999]: //ml/backend/ggml/ggml/src/ggml-cuda/fattn-wmma-f16.cu:437: ERROR: CUDA kernel flash_attn_ext_f16 has no device code compatible with CUDA arch 720. ggml-cuda.cu was compiled for: __CUDA_ARCH_LIST__ Fixes #12442 |
||
|---|---|---|
| .. | ||
| llm_darwin.go | ||
| llm_linux.go | ||
| llm_windows.go | ||
| memory.go | ||
| memory_test.go | ||
| server.go | ||
| server_test.go | ||
| status.go | ||