AlpinDale 89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745) 4 mesi fa
..
__init__.py 89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745) 4 mesi fa
arctic.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
baichuan.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
bart.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
blip.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
blip2.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
bloom.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
chameleon.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
chatglm.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
clip.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
commandr.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
dbrx.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
decilm.py 3f712cd287 feat: add progress bar for loading individual weight modules (#640) 4 mesi fa
deepseek.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
deepseek_v2.py 4ec08af18b chore: update fused MoE weight loading (#700) 4 mesi fa
exaone.py 08711d2ac9 feat: add Exaone model support (#743) 4 mesi fa
falcon.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
fuyu.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
gemma.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
gemma2.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
gpt2.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
gpt_bigcode.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
gpt_j.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
gpt_neox.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
idefics2_vision_model.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 mesi fa
interfaces.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
intern_vit.py 3f712cd287 feat: add progress bar for loading individual weight modules (#640) 4 mesi fa
internlm2.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
internvl.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
jais.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
jamba.py d34e083c48 feat: add experts_int8 support (#730) 4 mesi fa
llama.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
llama_embedding.py 3f712cd287 feat: add progress bar for loading individual weight modules (#640) 4 mesi fa
llava.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
llava_next.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
mamba.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
mamba_cache.py bf88c8567e feat: mamba model support (#674) 4 mesi fa
medusa.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
minicpm.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
minicpmv.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
mixtral.py 4ec08af18b chore: update fused MoE weight loading (#700) 4 mesi fa
mixtral_quant.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
mlp_speculator.py 3f712cd287 feat: add progress bar for loading individual weight modules (#640) 4 mesi fa
mpt.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
na_vit.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 mesi fa
nemotron.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
olmo.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
opt.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
orion.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
paligemma.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
persimmon.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
phi.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
phi3_small.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
phi3v.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
qwen.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
qwen2.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
qwen2_moe.py 4ec08af18b chore: update fused MoE weight loading (#700) 4 mesi fa
siglip.py 0b8b407b6d feat: support profiling with multiple multi-modal inputs per prompt (#712) 4 mesi fa
solar.py 0c6f03b7e4 feat: add Solar model support (#701) 4 mesi fa
stablelm.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
starcoder2.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa
utils.py 3693028340 feat: support for Audio modality (#698) 4 mesi fa
xverse.py 0e558e9b2f fix: loading chameleon model with TP>1 (#695) 4 mesi fa