Quick start: Install bigdl-llm on windows gpu #10195
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
* support name mapping for mixtral * support mixtral mixed quantization * fix style * fix
Sure, I will rename and move the figs. |
|
The size of the two visual studio figures (i.e. fig1 and fig2) are too large - rescale the figures and put them side-by-side. |
|
I don't think we need fig3. Add a figure to use windows task manager to check iGPU/GPU status, etc. |
shane-huang
reviewed
Feb 21, 2024
| 1. Step 1: Run the commands below in Anaconda prompt. | ||
|
|
||
| ```bash | ||
| conda create -n llm python=3.9 libuv # Already done in "Install conda" section |
There was a problem hiding this comment.
you already created llm env before, so just remove this line to avoid confusing.
| ```bash | ||
| conda create -n llm python=3.9 libuv # Already done in "Install conda" section | ||
| conda activate llm | ||
| pip install dpcpp-cpp-rt==2024.0.2 mkl-dpcpp==2024.0.0 onednn==2024.0.0 # Already done in "Install oneAPI" section |
There was a problem hiding this comment.
remove one-api as it is done in previous section.
shane-huang
reviewed
Feb 21, 2024
| from transformers import AutoTokenizer, GenerationConfig | ||
| ``` | ||
|
|
||
| Then we use phi-1.5 as an example to show how to run the model with bigdl-llm on windows. |
There was a problem hiding this comment.
make the phi-1.5 example in a new section "A Quick Example"
shane-huang
reviewed
Feb 21, 2024
| generation_config = GenerationConfig(use_cache = True) | ||
|
|
||
| if __name__ == '__main__': | ||
| parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for phi-1_5 model') |
There was a problem hiding this comment.
Make this example as simple as possible without much code.
- remove arg parse section (put just arg values in code)
- remove timing code
- make the comments concise
* remove include and language option, select the corresponding dataset based on the model name in Run * change the nightly test time * change the nightly test time of harness and ppl
* Make Offline installer as default for win gpu doc for oneAPI * Small other fixes
…a/*/pom.xml (#10197) * Bump org.apache.commons:commons-compress in /scala/serving Bumps org.apache.commons:commons-compress from 1.21 to 1.26.0. --- updated-dependencies: - dependency-name: org.apache.commons:commons-compress dependency-type: direct:production ... Signed-off-by: dependabot[bot] <[email protected]> * Bumps org.apache.commons:commons-compress from 1.21 to 1.26.0. * Bumps org.apache.commons:commons-compress from 1.21 to 1.26.0. * Bumps org.apache.commons:commons-compress from 1.21 to 1.26.0. * Bumps org.apache.commons:commons-compress from 1.21 to 1.26.0. --------- Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Shaojun Liu <[email protected]>
* Add c-eval workflow and modify running files * Modify the chatglm evaluator file * Modify the ceval workflow for triggering test * Modify the ceval workflow file * Modify the ceval workflow file * Modify ceval workflow * Adjust the ceval dataset download * Add ceval workflow dependencies * Modify ceval workflow dataset download * Add ceval test dependencies * Add ceval test dependencies * Correct the result print * Fix the nightly test trigger time * Fix ChatGLM loading issue
* add esimd sdp support * fix style
* add quantize kv_cache for baichuan2-13b * style fix
* add mlp layer unit tests * add download baichuan-13b * exclude llama for now * install additional packages * rename bash file * switch to Baichuan2 * delete attention related code * fix name errors in yml file
* Add model loading time record in csv for all-in-one benchmark * Small fix * Small fix to number after .
* add iq2 examples * small fix * meet code review * fix * meet review * small fix
jason-dai
changed the title
jason-dai
reviewed
Feb 22, 2024
Comment on lines
46
to
53
| * Run the commands below in Anaconda prompt. Please note that transformer version should match the model you want to use. For example, here we use transformers 4.37.0 to run the demo. | ||
|
|
||
| ```bash | ||
| conda activate llm | ||
|
|
||
| pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu | ||
| pip install transformers==4.37.0 | ||
| ``` |
There was a problem hiding this comment.
Move transformers related info to the example section
jason-dai
reviewed
Feb 22, 2024
Comment on lines
56
to
65
| * Now we can test whether all the components have been installed correctly. If we can import all the packages correctly following the python file below, then the installation is correct. | ||
| ```python | ||
| import torch | ||
| import time | ||
| import argparse | ||
| import numpy as np | ||
|
|
||
| from bigdl.llm.transformers import AutoModel,AutoModelForCausalLM | ||
| from transformers import AutoTokenizer, GenerationConfig | ||
| ``` |
There was a problem hiding this comment.
How does the user run this? Maybe it's easy to run it in the python prompt?
jason-dai
reviewed
Feb 22, 2024
| print('-'*20, 'Output', '-'*20) | ||
| print(output_str) | ||
| ``` | ||
| Here is the sample output on the laptop equipped with 11th Gen Intel(R) Core(TM) i7-1185G7 and Intel(R) Iris(R) Xe Graphics after running the example program above. |
There was a problem hiding this comment.
How does the user run this example?
There was a problem hiding this comment.
We provide the contents of demo.py and users could run it as python demo.py.
Update IPEX to 2.2.0+cpu and refactor for _ipex_optimize.
* optimize * update * fix style & move use_fuse_rope * add ipex version check * fix style * update * fix style * meet comments * address comments * fix style
…nto install-win-gpu
|
clean up the unused files. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Quick start: Install bigdl-ll on windows gpu