youkaichao eebad39f26 [torch.compile] support all attention backends (#10558) ...

Signed-off-by: youkaichao <youkaichao@gmail.com>

2024-11-22 14:04:42 -08:00

..

__init__.py

…

arctic.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

baichuan.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

bart.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

bert.py

…

blip2.py

…

blip.py

…

bloom.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

chameleon.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

chatglm.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

clip.py

[Model] Add Support for Multimodal Granite Models (#10291)

2024-11-21 10:46:20 +00:00

commandr.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

dbrx.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

decilm.py

…

deepseek_v2.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

deepseek.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

eagle.py

…

exaone.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

falcon.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

florence2.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

fuyu.py

…

gemma2.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

gemma.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

glm4_vision_encoder.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

gpt2.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

gpt_bigcode.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

gpt_j.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

gpt_neox.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

granite.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

granitemoe.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

h2ovl.py

…

idefics2_vision_model.py

…

idefics3.py

…

interfaces_base.py

…

interfaces.py

…

intern_vit.py

…

internlm2_ve.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

internlm2.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

internvl.py

[Model] Expose dynamic_image_size as mm_processor_kwargs for InternVL2 models (#10518)

2024-11-21 14:20:08 +00:00

jais.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

jamba.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

llama.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

llava_next_video.py

…

llava_next.py

[Model] Add Support for Multimodal Granite Models (#10291)

2024-11-21 10:46:20 +00:00

llava_onevision.py

…

llava.py

[Model] Add Support for Multimodal Granite Models (#10291)

2024-11-21 10:46:20 +00:00

mamba_cache.py

…

mamba.py

[Bugfix] Fix Mamba model initialization and MLP Speculator weights loading (#10456)

2024-11-20 05:04:05 +00:00

medusa.py

[model] Reduce medusa weight (#10454)

2024-11-20 06:05:55 +00:00

minicpm3.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

minicpm.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

minicpmv.py

…

mixtral_quant.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

mixtral.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

mllama.py

…

mlp_speculator.py

[Bugfix] Fix Mamba model initialization and MLP Speculator weights loading (#10456)

2024-11-20 05:04:05 +00:00

module_mapping.py

…

molmo.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

mpt.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

nemotron.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

nvlm_d.py

…

olmo.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

olmoe.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

opt.py

…

orion.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

paligemma.py

…

persimmon.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

phi3_small.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

phi3.py

…

phi3v.py

…

phi.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

phimoe.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

pixtral.py

[Model] Add Support for Multimodal Granite Models (#10291)

2024-11-21 10:46:20 +00:00

qwen2_audio.py

[Bugfix] Allow token ID-only inputs in Qwen2-Audio (#10536)

2024-11-21 18:09:43 +00:00

qwen2_cls.py

…

qwen2_moe.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

qwen2_rm.py

…

qwen2_vl.py

[torch.compile] limit inductor threads and lazy import quant (#10482)

2024-11-20 18:36:33 -08:00

qwen2.py

…

qwen.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

registry.py

…

roberta.py

…

siglip.py

[Model] Add Support for Multimodal Granite Models (#10291)

2024-11-21 10:46:20 +00:00

solar.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

stablelm.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

starcoder2.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00

ultravox.py

…

utils.py

[Platform][Refactor] Extract func get_default_attn_backend to Platform (#10358)

2024-11-19 11:22:26 +08:00

xverse.py

[torch.compile] support all attention backends (#10558)

2024-11-22 14:04:42 -08:00