Comments (4)
kadeng
commented on June 8, 2024
Thanks for reporting this. I brought this to the attention of the core development team, and will come back to you. We're striving for numerical equivalence, so we might consider this to be a bug.
from aitemplate.
kadeng
commented on June 8, 2024
As a quick update: The cutlass library underlying AITemplate's GEMM Kernels is using tf32 with some accuracy-enhancing trick by default on A100 / SM80+ GPUs, it seems. See https://github.com/NVIDIA/cutlass/blob/main/examples/27_ampere_3xtf32_fast_accurate_tensorop_gemm/27_ampere_3xtf32_fast_accurate_tensorop_gemm.cu - the numerical differences you are seeing are likey a result of this.
from aitemplate.
kadeng
commented on June 8, 2024
@zhekunz2 the PR above should address this issue.
from aitemplate.
zhekunz2
commented on June 8, 2024
@kadeng Thanks for the quick reply and fix! This fix works for me. Much appreciated! 🙏
from aitemplate.
Related Issues (20)
- fx2ait install error -- c10::StorageImpl has no member named mutable_data HOT 1
- AIT seems not able to achieve max along a given dim HOT 9
- complie controlnet error HOT 2
- Stable Diffusion (GLIGEN) Download Error HOT 4
- Building rocm docker image is very slow. Is there a prebuilt docker image? HOT 1
- error during inferencing: Error: Constant embeddings_token_embedding_weight was not set! Set the value with set_constant. HOT 2
- Failed to compile the controlnet: thepowefuldeez/sd21-controlnet-canny HOT 1
- gemm_gen_profiler() takes 3 positional arguments but 4 were given HOT 2
- <class 'src.pipeline_stable_diffusion_ait.StableDiffusionAITPipeline'> is incorrectly implemented. Expected {'feature_extractor', 'scheduler', 'tokenizer', 'text_encoder', 'safety_checker', 'unet', 'vae'} to be defined HOT 3
- `Fatal Python error: Floating point exception` with `run_with_tensors` HOT 3
- gcc: internal compiler error HOT 2
- `Unsupported workload for this conv2d specialization` when using dynamic shape together with permute HOT 6
- Does AIT handle if/else in forward function? HOT 1
- multi-gpu at runtime error HOT 4
- windows platform cannot link _binary_constants_bin_end and _binary_constants_bin_start HOT 5
- Model is successfully compiled, but OOM when loading
- Does Concatenate order matters? HOT 1
- Docker image fails to build due to python dependency issue HOT 2
- Got cutlass error: Error Internal at: 214 HOT 1
- model_interface.cu:231: Error: Constant pretrained_model_patch_embed_proj_weight was not set! Set the value with set_constant. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from aitemplate.