Cyrus Leung ef9baee3c5

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

..

__init__.py

[Speculative Decoding] EAGLE Implementation with Top-1 proposer (#6830)

2024-08-22 02:42:24 -07:00

arctic.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

baichuan.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

bart.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

blip2.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

blip.py

[Model] Add UltravoxModel and UltravoxConfig (#7615)

2024-08-21 22:49:39 +00:00

bloom.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

chameleon.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

chatglm.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

clip.py

[Model] Add multi-image input support for LLaVA-Next offline inference (#7230)

2024-08-28 07:09:02 +08:00

commandr.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

dbrx.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

decilm.py

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

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

deepseek_v2.py

[Misc] Update Fused MoE weight loading (#7334)

2024-08-13 14:57:45 -04:00

deepseek.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

eagle.py

[Speculative Decoding] EAGLE Implementation with Top-1 proposer (#6830)

2024-08-22 02:42:24 -07:00

falcon.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

fuyu.py

[Core][VLM] Stack multimodal tensors to represent multiple images within each prompt (#7902)

2024-08-28 01:53:56 +00:00

gemma2.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

gemma.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

gpt2.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

gpt_bigcode.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

gpt_j.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

gpt_neox.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

idefics2_vision_model.py

[Model]Refactor MiniCPMV (#7020)

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

interfaces.py

[VLM][Core] Support profiling with multiple multi-modal inputs per prompt (#7126)

2024-08-14 17:55:42 +00:00

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] Add AWQ quantization support for InternVL2 model (#7187)

2024-08-20 23:18:57 -07:00

internvl.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

jais.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

jamba.py

[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7766)

2024-08-27 15:07:09 -07:00

llama_embedding.py

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

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

llama.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

llava_next.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

llava.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

medusa.py

[Speculative Decoding] EAGLE Implementation with Top-1 proposer (#6830)

2024-08-22 02:42:24 -07:00

minicpm.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

minicpmv.py

[Core][VLM] Stack multimodal tensors to represent multiple images within each prompt (#7902)

2024-08-28 01:53:56 +00:00

mixtral_quant.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

mixtral.py

[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7766)

2024-08-27 15:07:09 -07:00

mlp_speculator.py

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

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

mpt.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

na_vit.py

[Model]Refactor MiniCPMV (#7020)

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

nemotron.py

[Model] Align nemotron config with final HF state and fix lm-eval-small (#7611)

2024-08-16 15:56:34 -07:00

olmo.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

opt.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

orion.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

paligemma.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

persimmon.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

phi3_small.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

phi3v.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

phi.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

qwen2_moe.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

qwen2.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

qwen.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

siglip.py

[Model] Add multi-image input support for LLaVA-Next offline inference (#7230)

2024-08-28 07:09:02 +08:00

stablelm.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00

starcoder2.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

ultravox.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

utils.py

[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)

2024-08-28 08:11:18 -07:00

xverse.py

[Bugfix] support tie_word_embeddings for all models (#5724)

2024-08-19 20:00:04 -07:00