SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

add shared experts for upcoming Granite 4.0 language models (#35894)

Browse Source 
* Modular GraniteMoE with shared Experts.

Signed-off-by: Shawn Tan <shawntan@ibm.com>

* Modified

* Import order.

* Modified for style

* Fix space.

* Test

* Remove extra granitemoe file.

* New converted file and tests

* Modified __init__ files.

* Formatting.

* Dummy PT objects

* register granitemoe shared model

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

* fix linting of a file

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

* fix import in modeling file

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

* update generated modeling file

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

* add documentation

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

* update docstrings

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

* update generated modeling file

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

* fix docstrings in config class

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

* merge main

Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>

---------

Signed-off-by: Shawn Tan <shawntan@ibm.com>
Signed-off-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>
Co-authored-by: Shawn Tan <shawntan@ibm.com>
Co-authored-by: Shawn Tan <shawn@wtf.sg>
Co-authored-by: Sukriti-Sharma4 <sukriti.sharma4@ibm.com>
Co-authored-by: Sukriti Sharma <Ssukriti@users.noreply.github.com>
This commit is contained in:
Mayank Mishra
2025-02-14 10:55:28 -05:00
committed by GitHub
parent 7ae7e87a09
commit a570e2ba87
15 changed files with 2517 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/perf_infer_gpu_one.md
View File

@@ -60,6 +60,7 @@ FlashAttention-2 is currently supported for the following architectures:
* [GPT-J](https://huggingface.co/docs/transformers/model_doc/gptj#transformers.GPTJModel)
* [Granite](https://huggingface.co/docs/transformers/model_doc/granite#transformers.GraniteModel)
* [GraniteMoe](https://huggingface.co/docs/transformers/model_doc/granitemoe#transformers.GraniteMoeModel)
* [GraniteMoeShared](https://huggingface.co/docs/transformers/model_doc/granitemoeshared#transformers.GraniteMoeSharedModel)
* [Idefics2](https://huggingface.co/docs/transformers/model_doc/idefics2#transformers.Idefics2Model)
* [Idefics3](https://huggingface.co/docs/transformers/model_doc/idefics3#transformers.Idefics3Model)
* [Falcon](https://huggingface.co/docs/transformers/model_doc/falcon#transformers.FalconModel)
@@ -266,6 +267,7 @@ For now, Transformers supports SDPA inference and training for the following arc
* [Idefics3](https://huggingface.co/docs/transformers/model_doc/idefics3#transformers.Idefics3Model)
* [I-JEPA](https://huggingface.co/docs/transformers/model_doc/ijepa#transformers.IJepaModel)
* [GraniteMoe](https://huggingface.co/docs/transformers/model_doc/granitemoe#transformers.GraniteMoeModel)
* [GraniteMoeShared](https://huggingface.co/docs/transformers/model_doc/granitemoeshared#transformers.GraniteMoeSharedModel)
* [JetMoe](https://huggingface.co/docs/transformers/model_doc/jetmoe#transformers.JetMoeModel)
* [Jamba](https://huggingface.co/docs/transformers/model_doc/jamba#transformers.JambaModel)
* [Llama](https://huggingface.co/docs/transformers/model_doc/llama#transformers.LlamaModel)