nvidia
/

Llama-3_1-Nemotron-51B-Instruct

Text Generation

Model card Files Files and versions Community

Llama-3_1-Nemotron-51B-Instruct / variable_cache.py

Commit History

fixed cache over-alloc bug (#17)

20cc7f1
verified

tomer-nv commited on 30 days ago

add batch_size attribute to VariableCache (#15)

e5d0706
verified

itlevy commited on Sep 30

v4.46 support (#7)

e9d0db3
verified

itlevy commited on Sep 26

v4.45 support (#6)

d311379
verified

itlevy commited on Sep 26

transformers>=4.44.2, backward compat

b5dfaf4
verified

itlevy commited on Sep 24