aws-neuron
/

optimum-neuron-cache

dacorvo HF staff commited on Sep 27

Commit

7b0370b

•

1 Parent(s): a785565

Update inference-cache-config/Llama3.1-70b.json

Files changed (1) hide show

inference-cache-config/Llama3.1-70b.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "meta-llama/Llama-3.1-70B": [
     {
       "batch_size": 1,
       "sequence_length": 4096,

 {
+  "meta-llama/Llama-3.1-70B-Instruct": [
     {
       "batch_size": 1,
       "sequence_length": 4096,