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