Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add gaudi modeling support in itrex #1438

Merged
merged 28 commits into from
May 24, 2024
Merged

add gaudi modeling support in itrex #1438

merged 28 commits into from
May 24, 2024

Conversation

ClarkChin08
Copy link
Contributor

Type of Change

gaudi modeling used in itrex for int4 kv-cache support

Signed-off-by: Clark Chin <xi2.chen@intel.com>
Copy link

github-actions bot commented Mar 29, 2024

⚡ Required checks status: All passing 🟢

Groups summary

🟢 Format Scan Tests workflow
Check ID Status Error details
format-scan (pylint) success
format-scan (bandit) success
format-scan (cloc) success
format-scan (cpplint) success

These checks are required after the changes to intel_extension_for_transformers/neural_chat/examples/finetuning/multi_modal/eval/mmmu_eval/run_llava.py, intel_extension_for_transformers/neural_chat/models/model_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/configuration_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/stopping_criteria.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/modeling_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/modeling_albert.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/modeling_bart.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip_text.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/modeling_bloom.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/modeling_codegen.py and 39 more files...

🟢 Optimize Unit Test workflow
Check ID Status Error details
optimize-unit-test-baseline success
optimize-unit-test-PR-test success
Genreate-OptimizeUT-Report success

These checks are required after the changes to intel_extension_for_transformers/transformers/modeling/modeling_gaudi/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/configuration_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/stopping_criteria.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/modeling_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/modeling_albert.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/modeling_bart.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip_text.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/modeling_bloom.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/modeling_codegen.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/esm/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/esm/modeling_esmfold.py and 36 more files...

🟢 NeuralChat Unit Test
Check ID Status Error details
neuralchat-unit-test-baseline success
neuralchat-unit-test-PR-test success
Generate-NeuralChat-Report success

These checks are required after the changes to intel_extension_for_transformers/neural_chat/models/model_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/configuration_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/stopping_criteria.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/modeling_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/modeling_albert.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/modeling_bart.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip_text.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/modeling_bloom.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/modeling_codegen.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/esm/__init__.py and 37 more files...

🟢 Engine Unit Test workflow
Check ID Status Error details
engine-unit-test-baseline success
engine-unit-test-PR-test success
Genreate-Engine-Report success

These checks are required after the changes to intel_extension_for_transformers/transformers/modeling/modeling_gaudi/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/configuration_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/stopping_criteria.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/modeling_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/modeling_albert.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/modeling_bart.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip_text.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/modeling_bloom.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/modeling_codegen.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/esm/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/esm/modeling_esmfold.py and 36 more files...

🟢 Chat Bot Test workflow
Check ID Status Error details
call-inference-llama-2-7b-chat-hf / inference test success
call-inference-mpt-7b-chat / inference test success

These checks are required after the changes to intel_extension_for_transformers/neural_chat/models/model_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/configuration_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/stopping_criteria.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/generation/utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/modeling_utils.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/albert/modeling_albert.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bart/modeling_bart.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/blip/modeling_blip_text.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/bloom/modeling_bloom.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/__init__.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/codegen/modeling_codegen.py, intel_extension_for_transformers/transformers/modeling/modeling_gaudi/models/esm/__init__.py and 37 more files...


Thank you for your contribution! 💜

Note
This comment is automatically generated and will be updates every 180 seconds within the next 6 hours. If you have any other questions, contact VincyZhang or XuehaoSun for help.

ClarkChin08 and others added 4 commits April 9, 2024 11:22
Signed-off-by: Chen Xi <xi2.chen@intel.com>
Signed-off-by: Chen Xi <xi2.chen@intel.com>
Copy link
Collaborator

@airMeng airMeng left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

no requirements updated? At least optimum-habana shall be added

airMeng and others added 2 commits April 24, 2024 16:23
Signed-off-by: Meng, Hengyu <hengyu.meng@intel.com>
Signed-off-by: Chen Xi <xi2.chen@intel.com>
@ClarkChin08
Copy link
Contributor Author

@lkk12014402 kaokao, please take a look on the new commit on measurement of ppl

Signed-off-by: Chen Xi <xi2.chen@intel.com>
zhentaoyu and others added 7 commits May 22, 2024 09:57
* initial commit

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* mv example

Signed-off-by: Yu Zhentao <zhentao.yu@intel.com>

* update model dtype

Signed-off-by: Yu Zhentao <zhentao.yu@intel.com>

* fix multi-round generation without streaming_llm

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* add mem and token num log

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* rebase

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* initial fp8

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* add ppl eval scripts

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* typo

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* add llama2-13b ppl eval script (align paper)

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* hide kv cache operation inside (v0.1)

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* hide kv cache operation inside (v0.2)

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* hide kv cache operation inside (v0.3)

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* update scripts

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* add README

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* update test scripts

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* remove useless code

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

* update README and rename shell scripts

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>

---------

Signed-off-by: Yu, Zhentao <zhentao.yu@intel.com>
Signed-off-by: Yu Zhentao <zhentao.yu@intel.com>
Signed-off-by: Clark Chin <xi2.chen@intel.com>
Signed-off-by: Chen Xi <xi2.chen@intel.com>
Signed-off-by: Clark Chin <xi2.chen@intel.com>
VincyZhang and others added 2 commits May 22, 2024 01:25
Signed-off-by: Chen Xi <xi2.chen@intel.com>
VincyZhang and others added 9 commits May 22, 2024 05:32
Signed-off-by: Clark Chin <xi2.chen@intel.com>
Signed-off-by: Clark Chin <xi2.chen@intel.com>
Signed-off-by: Clark Chin <xi2.chen@intel.com>
Signed-off-by: VincyZhang <wenxin.zhang@intel.com>
Signed-off-by: Clark Chin <xi2.chen@intel.com>
Signed-off-by: Clark Chin <xi2.chen@intel.com>
Copy link
Collaborator

@airMeng airMeng left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Great start on HPU

Signed-off-by: Clark Chin <xi2.chen@intel.com>
@VincyZhang VincyZhang merged commit 266e055 into main May 24, 2024
22 checks passed
@VincyZhang VincyZhang deleted the gaudi-support branch May 24, 2024 02:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants