Comments (11)
addition
python 3.6 with conda
from fastertransformer.
You are testing fp16 or fp32?
For fp16, if the diff number is something like 0.02, the answer is right.
from fastertransformer.
fp32,and the max diff is 3.
I compile the code without any modify.
and run the transformer_fp32.py,it returns cross check fail
from fastertransformer.
What commands do you use to run the transformer_fp32.py?
Did you specify the -DSM when compiling the code? Did you generate a new gemm_config.in?
from fastertransformer.
gemm_config.in was generate by gemmfp32
DSM i have try 60 61 70 75
I run the check with commond "transformer_fp32.py 2 2 2 2 2" .And some other parmamters, but all of them are wrong ,except 1 1 1 1 1 .
from fastertransformer.
Please try with some common configurations. For example, python transformer_fp32.py 1 12 128 12 64 to test the case batch size = 1, seq_len = 128, 12 layers with bert base.
from fastertransformer.
2 2 2 2 2 are meaningless parameters. Especially the settings of the head_num and size_per_head.
from fastertransformer.
here is the result of "python transformer_fp32.py 1 12 128 12 64 "
cross_check False
max diff 4.412327
min diff 6.79539e-06
maybe there is something wrong with abi ?
from fastertransformer.
What GPU do you use? What DSM values did you set?
What's the content of the gemm_config.in you generated?
from fastertransformer.
GPU is tesla M40,Driver Version: 418.67
DSM, i had try 60 61 70
gemm_config.in is
"13
13
13
6
2
"
from fastertransformer.
The compute capability of M40 is 52. You can have a try but I am not sure whether the code can be executed correctly on M40.
from fastertransformer.
Related Issues (20)
- terminate called after throwing an instance of 'std::runtime_error'
- src/fastertransformer/kernels/decoder_masked_multihead_attention /decoder_masked_multihead_attention_template.hpp:36 open this macro definition, it'll find a build error
- How to calculate local batch size?
- CUDA code compile error with clang: function template partial specialization is not allowed
- Incorrect inline ptx device assembly code usage
- cuSPARSELt is slower? HOT 1
- Whether fastertransformer supports gpt-2 classification model, such as GPT2ForSequenceClassification?
- Supporting for expert parallelism in MoE inference
- Is llama2 70b supported? Do you know minimal configuration? HOT 1
- How to serving multi-gpu inference? HOT 1
- How to get started?
- Sparsity support
- repetition_penalty logic in FT has bug HOT 1
- can support decoder only bart? such as MBartForCausalLM
- error You need C++17 to compile PyTorch
- Does FasterTransformer support multi-stream pipeline parallelism ?
- multi_block_mode performance issue HOT 1
- Confidence is not returned in the decoding example?
- on H800 can not exec nvidia/pytorch:23.09-py3 container success
- Are `fuseQKV masked attention` and Flash Attention the same?
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 fastertransformer.