vllm/models at e6e42e4b1759b8703bf6cb80aefa9c0ec35044f6 - vllm

__init__.py

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942 )

2024-08-06 16:51:47 -04:00

arctic.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

baichuan.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

bart.py

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942 )

2024-08-06 16:51:47 -04:00

blip2.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

blip.py

[Model] Initial support for BLIP-2 (#5920 )

2024-07-27 11:53:07 +00:00

bloom.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

chameleon.py

[Bugfix][Model] Skip loading lm_head weights if using tie_word_embeddings (#6758 )

2024-07-31 19:49:11 -07:00

chatglm.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

clip.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

commandr.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

dbrx.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

decilm.py

[Model] Add base class for LoRA-supported models (#5018 )

2024-06-27 16:03:04 +08:00

deepseek_v2.py

[Model] Pipeline Parallel Support for DeepSeek v2 (#6519 )

2024-07-23 12:22:09 -07:00

deepseek.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

falcon.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

fuyu.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

gemma2.py

[Misc] Support attention logits soft-capping with flash-attn (#7022 )

2024-08-01 13:14:37 -07:00

gemma.py

[Bugfix] Lower gemma's unloaded_params exception to warning (#7002 )

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

gpt2.py

[ Misc ] non-uniform quantization via compressed-tensors for Llama (#6515 )

2024-07-18 22:39:18 -04:00

gpt_bigcode.py

[Bugfix] GPTBigCodeForCausalLM: Remove lm_head from supported_lora_modules. (#6326 )

2024-07-11 07:05:59 -07:00

gpt_j.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

gpt_neox.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

idefics2_vision_model.py

[Model]Refactor MiniCPMV (#7020 )

2024-08-04 08:12:41 +00:00

interfaces.py

[Core] Support serving encoder/decoder models (#7258 )

2024-08-09 10:39:41 +08:00

intern_vit.py

[Model] Refactor and decouple weight loading logic for InternVL2 model (#7067 )

2024-08-02 22:36:14 -07:00

internlm2.py

[Model] Initialize support for InternVL2 series models (#6514 )

2024-07-29 10:16:30 +00:00

internvl.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

jais.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

jamba.py

[Model][Jamba] Mamba cache single buffer (#6739 )

2024-08-09 10:07:06 -04:00

llama_embedding.py

[Model][Misc] Add e5-mistral-7b-instruct and Embedding API (#3734 )

2024-05-11 11:30:37 -07:00

llama.py

[Core] Support loading GGUF model (#5191 )

2024-08-05 17:54:23 -06:00

llava_next.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

llava.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

medusa.py

[Speculative Decoding] Medusa Implementation with Top-1 proposer (#4978 )

2024-07-09 18:34:02 -07:00

minicpm.py

[Bugfix][Model] Skip loading lm_head weights if using tie_word_embeddings (#6758 )

2024-07-31 19:49:11 -07:00

minicpmv.py

[Model] Rename MiniCPMVQwen2 to MiniCPMV2.6 (#7273 )

2024-08-08 14:02:41 +00:00

mixtral_quant.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

mixtral.py

[ Misc ] non-uniform quantization via compressed-tensors for Llama (#6515 )

2024-07-18 22:39:18 -04:00

mlp_speculator.py

[Bugfix] Fix speculative decoding with MLPSpeculator with padded vocabulary (#7218 )

2024-08-08 22:08:46 -07:00

mpt.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

na_vit.py

[Model]Refactor MiniCPMV (#7020 )

2024-08-04 08:12:41 +00:00

nemotron.py

[Model] Support Nemotron models (Nemotron-3, Nemotron-4, Minitron) (#6611 )

2024-07-26 14:33:42 -04:00

olmo.py

[Bugfix][Model] Skip loading lm_head weights if using tie_word_embeddings (#6758 )

2024-07-31 19:49:11 -07:00

opt.py

[Model] Initial support for BLIP-2 (#5920 )

2024-07-27 11:53:07 +00:00

orion.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

paligemma.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

persimmon.py

[Model] Initialize Fuyu-8B support (#3924 )

2024-07-14 05:27:14 +00:00

phi3_small.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

phi3v.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

phi.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

qwen2_moe.py

[Model] Pipeline parallel support for Qwen2 (#6924 )

2024-07-31 18:49:51 -07:00

qwen2.py

[Core] Support loading GGUF model (#5191 )

2024-08-05 17:54:23 -06:00

qwen.py

[Models] Support Qwen model with PP (#6974 )

2024-08-01 12:40:43 -07:00

siglip.py

[Core][VLM] Support image embeddings as input (#6613 )

2024-08-12 16:16:06 +08:00

stablelm.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

starcoder2.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00

utils.py

[Model] Support SigLIP encoder and alternative decoders for LLaVA models (#7153 )

2024-08-06 16:55:31 +08:00

xverse.py

[CORE] Quantized lm-head Framework (#4442 )

2024-07-02 22:25:17 +00:00