Comments (4)
Vasud-ha
commented on June 3, 2024
2
@SAint7579 Thanks for reporting it, we will investigate and get back to you.
from intel-extension-for-pytorch.
Vasud-ha
commented on June 3, 2024
2
Hi @rskasturi, thanks for sharing the updates, we can reproduce the issue on our end and are currently in the process of debugging it.
from intel-extension-for-pytorch.
rskasturi
commented on June 3, 2024
Hey @Vasud-ha, the distortions seems to be observed with latest IPEX version(v2.1.20+xpu) as well.
from intel-extension-for-pytorch.
Vasud-ha
commented on June 3, 2024
The first output difference on CPU and GPU is occurring at this layer of the model.
image_tokenizer.model.embeddings.dropout
from intel-extension-for-pytorch.
Related Issues (20)
- IPEX.LLM performance on Intel SPR with large batch size. HOT 3
- [python][cpu][llm] run with THUDM/chatglm3-6b raise "RuntimeError: Unsupported input type" HOT 4
- OSError: [WinError 1920] The file cannot be accessed by the system. Error loading "C:\Users\techn\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\lib\backend_with_compiler.dll" or one of its dependencies. HOT 43
- test
- test
- initial import time of `torch` & `intel_extension_for_pytorch` is long on Windows Core Ultra HOT 3
- Incorrect inference output when not computing gradients on XPU HOT 8
- Run WOQ INT8 and WOQ INT4 in distributed way don't show token latency information even added --token-latency HOT 1
- Communication and compute on separate Streams do not overlap HOT 7
- How do you save a model after using WOQ? HOT 2
- Unable to run llama_cpp example from quickstart guide (PI_ERROR_BUILD_PROGRAM_FAILURE)
- failed to run on ultra 5 with Arc(TM) graphics (16GB VRAM) HOT 5
- compatability issues with oobabooga HOT 8
- operator does not exist for XPU backend
- IPEX takes 10min+ for "warmup" on MTL iGPU HOT 1
- Failed to run interger matrix multiply HOT 3
- Error can't import the library: Key already registered with the same priority HOT 2
- How to use ipex.llm.optimize HOT 1
- IFFTRN Arguments RuntimeError: FFT_INVALID_DESCRIPTOR HOT 3
- model.to('xpu') does not terminate HOT 3
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 intel-extension-for-pytorch.