We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I'm moving this discussion to a new issue since it is different from #32.
To summarize: When I run diffusion_rs_cli (without CUDA support), it errors right after asking for the prompt.
diffusion_rs_cli
diffusion_rs_cli --scale 3.5 --num-steps 50 dduf -f FLUX.1-dev-Q4-bnb.dduf 2025-01-09T18:44:36.528527Z INFO diffusion_rs_core::pipelines: loading from source: dduf file: FLUX.1-dev-Q4-bnb.dduf. 2025-01-09T18:44:36.528909Z INFO diffusion_rs_core::pipelines: model architecture is: flux 2025-01-09T18:44:36.529194Z INFO diffusion_rs_core::util::auto_dtype: dtype selected is F16. 2025-01-09T18:44:36.582729Z INFO diffusion_rs_core::pipelines::flux: loading CLIP model 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 196/196 [00:00<00:00, 2446.43it/s] 2025-01-09T18:44:36.868689Z INFO diffusion_rs_core::pipelines::flux: loading T5 model 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 138/138 [00:00<00:00, 526.65it/s] 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 513/513 [00:02<00:00, 463.28it/s] 2025-01-09T18:44:41.174098Z INFO diffusion_rs_core::pipelines::flux: loading VAE model 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 244/244 [00:00<00:00, 5353.65it/s] 2025-01-09T18:44:41.484905Z INFO diffusion_rs_core::pipelines::flux: loading FLUX model 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2672/2672 [00:05<00:00, 605.08it/s] 2025-01-09T18:44:47.498607Z INFO diffusion_rs_core::pipelines::flux: FLUX pipeline using a guidance-distilled model: true ◇ Height: │ 720 │ ◇ Width: │ 1280 │ ◇ Prompt: │ something │ Error: dtype mismatch in matmul_with_alpha, lhs: F16, rhs: BF16
I built it as following, the last commit was 1d1f0bf (#34):
cargo install --git https://github.com/EricLBuehler/diffusion-rs
The text was updated successfully, but these errors were encountered:
I got a backtrace with RUST_BACKTRACE=1:
RUST_BACKTRACE=1
Error: dtype mismatch in matmul_with_alpha, lhs: F16, rhs: BF16 0: diffusion_rs_common::core::error::Error::bt 1: diffusion_rs_common::core::storage::Storage::same_dtype 2: diffusion_rs_common::core::tensor::Tensor::matmul 3: <diffusion_rs_backend::bitsandbytes::BnbLinear as diffusion_rs_backend::QuantMethod>::forward 4: diffusion_rs_backend::QuantMethod::forward_autocast 5: diffusion_rs_core::models::t5::T5EncoderModel::forward 6: <diffusion_rs_core::pipelines::flux::FluxPipeline as diffusion_rs_core::pipelines::ModelPipeline>::forward 7: diffusion_rs_cli::main 8: std::sys::backtrace::__rust_begin_short_backtrace 9: main 10: <unknown> 11: __libc_start_main 12: _start Stack backtrace: 0: anyhow::error::<impl core::convert::From<E> for anyhow::Error>::from 1: diffusion_rs_cli::main 2: std::sys::backtrace::__rust_begin_short_backtrace 3: main 4: <unknown> 5: __libc_start_main 6: _start
Sorry, something went wrong.
No branches or pull requests
I'm moving this discussion to a new issue since it is different from #32.
To summarize: When I run
diffusion_rs_cli
(without CUDA support), it errors right after asking for the prompt.Click to see output
I built it as following, the last commit was 1d1f0bf (#34):
The text was updated successfully, but these errors were encountered: