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