Comments (3)
vpirogov
commented on September 26, 2024
@oleotiger, we are working on enabling per-group quantization in oneDNN. You can find description of proposed design for fused weight decompression here. Implementation is not yet available for any platforms though. The only option for now is to decompress weights separately, as you indicated.
from onednn.
vpirogov
commented on September 26, 2024
from onednn.
vpirogov
commented on September 26, 2024
API and validation changes necessary to support W8A16 quantization landed to main and rls-v3.4 branches. Specifics is covered in GPT Quantization RFC.
+@jondea, @milpuz01 for additional comments on Arm specifics.
from onednn.
Related Issues (20)
- New/other Matrix multiplication algorithm implementation HOT 11
- Bnorm tests are mistrusted on aarch64 HOT 1
- Mean used for lnorm benchmark is not actual mean of the data HOT 2
- Does oneDNN support int64? HOT 2
- Clarification Needed on Memory Requirements for Batch Matrix Multiplication Description HOT 3
- Working with the Reorder HOT 10
- Performance with matmul HOT 9
- DNNL_TEST_SET NIGHTLY produces duplicate benchdnn tests HOT 1
- AMD oneDNN Build Error HOT 2
- could not create a primitive descriptor for a reorder primitive HOT 11
- Speed drop when running oneDNN in a subthread HOT 11
- python call sycl C++ Error
- brgconv:sve_256 uses a lot of memory HOT 4
- brg:sve_256 fails benchdnn accuracy tests
- The testcase test_graph_unit_dnnl_layer_norm_usm_cpu fails HOT 7
- Pytorch bias quantisation on aarch64 - how best to proceed? HOT 3
- Fix compilation of oneDNN with C++20 on Windows HOT 4
- [ACL] non-constant depthwise convolution weights leads to performance degradation HOT 2
- Build with SYCL fails using intel/llvm compiler HOT 5
- OneDNN 2.7.3 Compilation Error in TensorFlow on RISC-V HOT 2
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 onednn.