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