Dipika Sikka 3989a79824 [Bugfix] Update starcoder2 to remap k/v scale names for kv_cache quantization (#11148)

2024-12-13 05:07:20 +00:00

..

__init__.py

[Misc] Rename embedding classes to pooling (#10801)

2024-12-01 14:36:51 +08:00

adapters.py

[Misc] Rename embedding classes to pooling (#10801)

2024-12-01 14:36:51 +08:00

arctic.py

…

aria.py

[Misc] Remove deprecated names (#10817)

2024-12-03 06:52:57 +00:00

baichuan.py

…

bart.py

…

bert.py

…

blip2.py

…

blip.py

[Model] Consolidate ViTs attention implementation without mask (#10893)

2024-12-04 18:11:08 +00:00

bloom.py

…

chameleon.py

…

chatglm.py

…

clip.py

[Model] Consolidate ViTs attention implementation without mask (#10893)

2024-12-04 18:11:08 +00:00

commandr.py

…

dbrx.py

…

decilm.py

…

deepseek_v2.py

…

deepseek.py

…

eagle.py

…

exaone.py

[Doc] Explicitly state that PP isn't compatible with speculative decoding yet (#10975)

2024-12-07 17:20:49 +00:00

falcon.py

…

florence2.py

…

fuyu.py

…

gemma2.py

…

gemma.py

…

glm4_vision_encoder.py

[Model] Consolidate ViTs attention implementation without mask (#10893)

2024-12-04 18:11:08 +00:00

glm.py

…

gpt2.py

…

gpt_bigcode.py

…

gpt_j.py

…

gpt_neox.py

…

granite.py

[Doc] Explicitly state that PP isn't compatible with speculative decoding yet (#10975)

2024-12-07 17:20:49 +00:00

granitemoe.py

…

gritlm.py

[Bugfix] Use runner_type instead of task in GritLM (#11144)

2024-12-13 04:09:53 +00:00

h2ovl.py

…

idefics2_vision_model.py

[Model] Consolidate ViTs attention implementation without mask (#10893)

2024-12-04 18:11:08 +00:00

idefics3.py

[Bugfix] Fix Idefics3 fails during multi-image inference (#11080)

2024-12-11 01:27:07 -08:00

interfaces_base.py

[Misc] Rename embedding classes to pooling (#10801)

2024-12-01 14:36:51 +08:00

interfaces.py

[Model] PP support for Mamba-like models (#10992)

2024-12-10 21:53:37 -05:00

intern_vit.py

[Model] Consolidate ViTs attention implementation without mask (#10893)

2024-12-04 18:11:08 +00:00

internlm2_ve.py

…

internlm2.py

…

internvl.py

[V1] Initial support of multimodal models for V1 re-arch (#10699)

2024-12-08 12:50:51 +00:00

jais.py

…

jamba.py

[Model] PP support for Mamba-like models (#10992)

2024-12-10 21:53:37 -05:00

llama.py

[Doc] Explicitly state that PP isn't compatible with speculative decoding yet (#10975)

2024-12-07 17:20:49 +00:00

llava_next_video.py

…

llava_next.py

…

llava_onevision.py

…

llava.py

[Bugfix] Quick fix to make Pixtral-HF load correctly again after 39e227c7ae. (#11024)

2024-12-12 18:09:20 +00:00

mamba_cache.py

…

mamba.py

[Model] PP support for Mamba-like models (#10992)

2024-12-10 21:53:37 -05:00

medusa.py

…

minicpm3.py

…

minicpm.py

[Model] support bitsandbytes quantization with minicpm model (#10842)

2024-12-03 03:06:41 +00:00

minicpmv.py

…

mixtral_quant.py

…

mixtral.py

…

mllama.py

…

mlp_speculator.py

…

module_mapping.py

…

molmo.py

[V1] Initial support of multimodal models for V1 re-arch (#10699)

2024-12-08 12:50:51 +00:00

mpt.py

…

nemotron.py

[Doc] Explicitly state that PP isn't compatible with speculative decoding yet (#10975)

2024-12-07 17:20:49 +00:00

nvlm_d.py

…

olmo2.py

…

olmo.py

…

olmoe.py

…

opt.py

…

orion.py

…

paligemma.py

…

persimmon.py

…

phi3_small.py

…

phi3.py

…

phi3v.py

[Model] merged input processor for Phi-3-Vision models (#10977)

2024-12-09 12:55:10 -08:00

phi.py

…

phimoe.py

…

pixtral.py

[Pixtral] Improve loading (#11040)

2024-12-10 06:09:32 +00:00

qwen2_audio.py

[Model] Composite weight loading for multimodal Qwen2 (#10944)

2024-12-07 07:22:52 -07:00

qwen2_cls.py

…

qwen2_moe.py

…

qwen2_rm.py

…

qwen2_vl.py

[Model] Composite weight loading for multimodal Qwen2 (#10944)

2024-12-07 07:22:52 -07:00

qwen2.py

[Model] Composite weight loading for multimodal Qwen2 (#10944)

2024-12-07 07:22:52 -07:00

qwen.py

…

registry.py

[Model] Add support for embedding model GritLM (#10816)

2024-12-12 06:39:16 +00:00

roberta.py

…

siglip.py

[Model] Consolidate ViTs attention implementation without mask (#10893)

2024-12-04 18:11:08 +00:00

solar.py

[Doc] Explicitly state that PP isn't compatible with speculative decoding yet (#10975)

2024-12-07 17:20:49 +00:00

stablelm.py

…

starcoder2.py

[Bugfix] Update starcoder2 to remap k/v scale names for kv_cache quantization (#11148)

2024-12-13 05:07:20 +00:00

telechat2.py

…

ultravox.py

…

utils.py

[V1] Initial support of multimodal models for V1 re-arch (#10699)

2024-12-08 12:50:51 +00:00