3 people e24113a8fe [Model] Refactor Qwen2-VL to use merged multimodal processor (#11258) ...

Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

2024-12-19 16:28:00 +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

[model][utils] add extract_layer_index utility function (#10599)

2024-11-23 22:22:54 -08:00

aria.py

[Misc] Remove deprecated names (#10817)

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

baichuan.py

[Misc]Further reduce BNB static variable (#10597)

2024-11-26 22:54:12 -08:00

bart.py

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

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

bert.py

[Bugfix] Ignore lm_head when loading embedding models (#10719)

2024-11-27 19:05:29 +00:00

blip2.py

[Model] Replace embedding models with pooling adapter (#10769)

2024-12-01 08:02:54 +08:00

blip.py

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

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

bloom.py

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

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

chameleon.py

[V1] Refactor model executable interface for multimodal models (#10570)

2024-11-26 20:46:11 +00:00

chatglm.py

[V1] Refactor model executable interface for multimodal models (#10570)

2024-11-26 20:46:11 +00:00

clip.py

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

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

commandr.py

[Model] Support Cohere2ForCausalLM (Cohere R7B) (#11203)

2024-12-16 09:56:19 +00:00

dbrx.py

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

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

decilm.py

[Misc] Add uninitialized params tracking for AutoWeightsLoader (#10327)

2024-11-18 09:07:46 +08:00

deepseek_v2.py

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

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

deepseek.py

[model][utils] add extract_layer_index utility function (#10599)

2024-11-23 22:22:54 -08:00

eagle.py

[V1] Refactor model executable interface for all text-only language models (#10374)

2024-11-17 05:18:46 +00:00

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

[Misc]Further reduce BNB static variable (#10597)

2024-11-26 22:54:12 -08:00

florence2.py

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

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

fuyu.py

[V1] Refactor model executable interface for multimodal models (#10570)

2024-11-26 20:46:11 +00:00

gemma2.py

[Model] Replace embedding models with pooling adapter (#10769)

2024-12-01 08:02:54 +08:00

gemma.py

[Misc]Further reduce BNB static variable (#10597)

2024-11-26 22:54:12 -08:00

glm4_vision_encoder.py

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

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

glm.py

[Model] Added GLM-4 series hf format model support vllm==0.6.4 (#10561)

2024-11-28 14:53:31 +00:00

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

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

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

granitemoe.py

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

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

gritlm.py

[Frontend] Separate pooling APIs in offline inference (#11129)

2024-12-13 10:40:07 +00:00

h2ovl.py

[1/N] Initial prototype for multi-modal processor (#10044)

2024-11-13 12:39:03 +00:00

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

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

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

internlm2.py

[Model] Add Internlm2 LoRA support (#5064)

2024-11-28 17:29:04 +00:00

internvl.py

[V1][VLM] Fix edge case bug for InternVL2 (#11165)

2024-12-13 11:09:30 +00:00

jais.py

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

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

jamba.py

[Model] Add JambaForSequenceClassification model (#10860)

2024-12-19 22:48:06 +08:00

llama.py

[Bugfix] Fix error handling of unsupported sliding window (#11213)

2024-12-15 10:59:42 -07:00

llava_next_video.py

[Model] Replace embedding models with pooling adapter (#10769)

2024-12-01 08:02:54 +08:00

llava_next.py

[Model] Replace embedding models with pooling adapter (#10769)

2024-12-01 08:02:54 +08:00

llava_onevision.py

[Model] Replace embedding models with pooling adapter (#10769)

2024-12-01 08:02:54 +08:00

llava.py

[VLM] Merged multimodal processor for Qwen2-Audio (#11303)

2024-12-19 06:14:17 +00:00

mamba_cache.py

[Kernel][Model] Improve continuous batching for Jamba and Mamba (#9189)

2024-10-16 12:12:43 -04:00

mamba.py

[core] clean up cudagraph batchsize padding logic (#10996)

2024-12-13 06:57:50 +00:00

medusa.py

[model] Reduce medusa weight (#10454)

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

minicpm3.py

[Model] Clean up MiniCPMV (#10751)

2024-11-29 04:47:06 +00:00

minicpm.py

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

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

minicpmv.py

[Model] Clean up MiniCPMV (#10751)

2024-11-29 04:47:06 +00:00

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

[Misc]Further reduce BNB static variable (#10597)

2024-11-26 22:54:12 -08:00

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

[Model][LoRA]LoRA support added for MiniCPMV2.5 (#7199)

2024-09-29 06:59:45 +00:00

molmo.py

[V1] Fix multimodal profiling for Molmo (#11325)

2024-12-19 16:27:22 +00:00

mpt.py

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

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

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

[Bugfix] Fix _init_vision_model in NVLM_D model (#9611)

2024-10-23 14:09:04 +00:00

olmo2.py

[Model] Add OLMo November 2024 model (#10503)

2024-11-25 17:26:40 -05:00

olmo.py

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

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

olmoe.py

[model][utils] add extract_layer_index utility function (#10599)

2024-11-23 22:22:54 -08:00

opt.py

[Misc]Further reduce BNB static variable (#10597)

2024-11-26 22:54:12 -08:00

orion.py

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

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

paligemma.py

PaliGemma 2 support (#11142)

2024-12-13 07:40:07 +00:00

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

[Misc]Further reduce BNB static variable (#10597)

2024-11-26 22:54:12 -08:00

phi3v.py

[VLM] Merged multimodal processor for Qwen2-Audio (#11303)

2024-12-19 06:14:17 +00:00

phi.py

[Misc]Further reduce BNB static variable (#10597)

2024-11-26 22:54:12 -08:00

phimoe.py

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

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

pixtral.py

[Bugfix] Cleanup Pixtral HF code (#11333)

2024-12-19 13:22:00 +00:00

qwen2_audio.py

[Model] Refactor Qwen2-VL to use merged multimodal processor (#11258)

2024-12-19 16:28:00 +00:00

qwen2_cls.py

[Misc] Add uninitialized params tracking for AutoWeightsLoader (#10327)

2024-11-18 09:07:46 +08:00

qwen2_moe.py

[model][utils] add extract_layer_index utility function (#10599)

2024-11-23 22:22:54 -08:00

qwen2_rm.py

[Misc] Add uninitialized params tracking for AutoWeightsLoader (#10327)

2024-11-18 09:07:46 +08:00

qwen2_vl.py

[Model] Refactor Qwen2-VL to use merged multimodal processor (#11258)

2024-12-19 16:28:00 +00:00

qwen2.py

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

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

qwen.py

[Misc]Further reduce BNB static variable (#10597)

2024-11-26 22:54:12 -08:00

registry.py

[Model] Add JambaForSequenceClassification model (#10860)

2024-12-19 22:48:06 +08:00

roberta.py

[Model] Enable optional prefix when loading embedding models (#10639)

2024-11-25 18:14:33 +00:00

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

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

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

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

[Model] Support telechat2 (#10311)

2024-11-27 11:32:35 +00:00

ultravox.py

[VLM] Merged multimodal processor for Qwen2-Audio (#11303)

2024-12-19 06:14:17 +00:00

utils.py

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

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