Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
Multi-LoRA cold compile test: read the source as utf-8 (#16531)
Daniel Han7f0620d65555
diff --git a/tests/test_multi_lora_cold_compile_cpu.py b/tests/test_multi_lora_cold_compile_cpu.pyindex a4d68af0301..a00d5e64f26 100644--- a/tests/test_multi_lora_cold_compile_cpu.py+++ b/tests/test_multi_lora_cold_compile_cpu.py@@ -30,7 +30,7 @@ def _load_experts():"_warn_once","_is_quantized",}- tree = ast.parse(path.read_text(), filename = str(path))+ tree = ast.parse(path.read_text(encoding = "utf-8"), filename = str(path))tree.body = [n for n in tree.body if isinstance(n, (ast.ClassDef, ast.FunctionDef)) and n.name in names]