mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 12:54:11 +08:00
f76fdcaaf8
Prune models from TorchInductor dashboard to reduce ci cost. This PR prunes for hugging face models according to the [doc](https://docs.google.com/document/d/1nLPNNAU-_M9Clx9FMrJ1ycdPxe-xRA54olPnsFzdpoU/edit?tab=t.0), which reduces from 46 to 27 models. Pull Request resolved: https://github.com/pytorch/pytorch/pull/164815 Approved by: https://github.com/anijain2305, https://github.com/seemethere, https://github.com/huydhn, https://github.com/malfet
40 lines
907 B
Plaintext
40 lines
907 B
Plaintext
AlbertForMaskedLM,8
|
|
AllenaiLongformerBase,8
|
|
BartForCausalLM,8
|
|
BertForMaskedLM,32
|
|
BlenderbotForCausalLM,32
|
|
BlenderbotForConditionalGeneration,16
|
|
DebertaV2ForMaskedLM,8
|
|
DistilBertForMaskedLM,256
|
|
DistillGPT2,32
|
|
ElectraForCausalLM,64
|
|
GPT2ForSequenceClassification,8
|
|
GPTJForCausalLM,1
|
|
GPTJForQuestionAnswering,1
|
|
GPTNeoForCausalLM,32
|
|
GPTNeoForSequenceClassification,32
|
|
GoogleFnet,32
|
|
LayoutLMForMaskedLM,32
|
|
M2M100ForConditionalGeneration,64
|
|
MBartForCausalLM,8
|
|
MT5ForConditionalGeneration,32
|
|
MegatronBertForCausalLM,16
|
|
MobileBertForMaskedLM,256
|
|
OPTForCausalLM,4
|
|
PLBartForCausalLM,16
|
|
PegasusForCausalLM,128
|
|
RobertaForCausalLM,32
|
|
T5ForConditionalGeneration,8
|
|
T5Small,8
|
|
TrOCRForCausalLM,64
|
|
XGLMForCausalLM,32
|
|
XLNetLMHeadModel,16
|
|
YituTechConvBert,32
|
|
meta-llama/Llama-3.2-1B,8
|
|
google/gemma-2-2b,8
|
|
google/gemma-3-4b-it,8
|
|
openai/whisper-tiny,8
|
|
Qwen/Qwen3-0.6B,8
|
|
mistralai/Mistral-7B-Instruct-v0.3, 8
|
|
openai/gpt-oss-20b, 8
|