Closed kunc01 closed 8 months ago
@kunc01 This problem has been fixed in the latest nightly release. Please try it.
@chengzeyi Thanks for your reply,I tried 1.0.2.dev20240127+torch211cu118 on a V100 and 1.0.2.dev20240127+torch211cu121 on a A10,but found new errors.
@chengzeyi Thanks for your reply,I tried 1.0.2.dev20240127+torch211cu118 on a V100 and 1.0.2.dev20240127+torch211cu121 on a A10,but found new errors.
Just fixed it. Please retry.
@chengzeyi
@chengzeyi
I guess this is related to Triton. can you try running with disabling Triton? Or you can share a minimal reproducing script so that I can reproduce it quickly.
@chengzeyi Inference succeeded with enable_triton = False
upsampler = StableDiffusionLatentUpscalePipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16).to("cuda")
config = CompilationConfig.Default()
config.enable_xformers = True
config.enable_triton = False
config.enable_cuda_graph = True
upsampler = compile(upsampler, config)
Hi! Thanks for your amazing work.
I've tested on a V100 GPU, stable-fast works perfect for
StableDiffusionControlNetInpaintPipeline
, but for latent-upscaler and corresponding StableDiffusionLatentUpscalePipeline,sfast.compilers.diffusion_pipeline_compiler.compile_unet
leads to, while vae and text_encoder still work well.
I've tried options like
enable_xformers
,enable_triton
,enable_cuda_graph
,prefer_lowp_gemm
andenable_fused_linear_geglu
, but the error persists.Looking forward to your reply, thank you!