Comments (1)
hi @lucshi
I'd like to use VTune to profiel IPEX application focusing on GPU. e.g. the performance/all-in-one benchmark to get a full picture of bottleneck. My questions are:
- General guide to use VTune to profile IPEX application.
You may refer to this doc https://www.intel.com/content/www/us/en/docs/oneapi/optimization-guide-gpu/2023-0/gpu-analysis-with-vtunetm-profiler.html and their cookbook of gpu https://www.intel.com/content/www/us/en/docs/vtune-profiler/cookbook/2024-2/profiling-dpc-application.html
- Which OS shall I choose for most profiling details? Whether Windows have some limitation like "layers level profiling is not available".
Both linux and window are ok. If you want a "layers level profiling", how about a torch profiler?
- How to map the source code with the possible profiling bottleneck result.
In theory, you can refer to this to do it. You can give it a try.
https://www.intel.com/content/www/us/en/docs/vtune-profiler/user-guide/2023-0/viewing-source.html
from bigdl.
Related Issues (20)
- vllm can‘t use oneCCL on host HOT 3
- Run InternLM2 , reports error:TypeError: internlm2_attention_forward() got an unexpected keyword argument 'cache_position' HOT 5
- [MTL][Internvl2-4B] GPU OOM for 3k input tokens
- Please provide a method to benchmark Multimodal InternVL-4B on MTL‘s iGPU HOT 6
- Ollama already occupying port before running ./ollama serve HOT 4
- minicpm-v-2-6 can't run on A770 Ubuntu HOT 4
- Lightweight-serving support for codegeex is broken HOT 1
- MiniCPM-V-2.6 load_low_bit fails HOT 4
- GPU memory continue increase when in Deepspeed TP benchmark HOT 3
- ollama runs gemma:2b, asks a question, does not answer, and reports no error. HOT 2
- failure load the Qwen2-72B-Instruct with FP6 on 4 ARC GPU HOT 1
- Failure to load the LLM model in vLLM on 8 ARC HOT 1
- New model support request
- Result is wrong when running Qwen2-1.5B-Instruct on Intel NPU HOT 2
- `Qwen/Qwen2-7B-Instruct` gives garbled outputs in LongBench with `load_in_low_bit="fp16"` and `optimize_model=False`
- MiniCPM-V-2_6 load_low_bit mode.chat fails on MTL iGPU
- Issue running throughput test with vllm on 4 Arc A770: "Current platform can NOT allocate memory block with size larger than 4GB! " HOT 2
- Inference produced repetitive and erroneous output by a fintuned qwen2 model HOT 1
- Running benchmark/all-in-one with GLM-4-9B-Chat model report "AutoTP not support for models"
- [Qwen2-Audio-7B-Instruct] model support
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 bigdl.