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