Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion config_explorer/Capacity_Planner.py
Original file line number Diff line number Diff line change
Expand Up @@ -326,7 +326,7 @@ def workload_specification():
with st.expander("See how KV cache is calculated below"):
st.write(f"""First, the per-token memory requirement is estimated given the following inputs:
- KV cache data type: `{kv_details.kv_data_type}` = {kv_details.precision_in_bytes} bytes in memory
- Hidden layers: {model_config.num_hidden_layers}
- Hidden layers: {text_config.num_hidden_layers}

This model uses _{kv_details.attention_type}_. The relevant parameters are:
""")
Expand Down