Skip to content

Commit

Permalink
fix ultravox model installations
Browse files Browse the repository at this point in the history
  • Loading branch information
Sri Tikkireddy committed Sep 20, 2024
1 parent 02083ad commit 6696c5f
Showing 1 changed file with 6 additions and 0 deletions.
6 changes: 6 additions & 0 deletions mlflow_extensions/databricks/prebuilt/audio/vllm.py
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,9 @@
trust_remote_code=True,
guided_decoding_backend="outlines",
max_model_len=64000,
library_overrides={
"vllm": '"vllm[audio]==0.6.0"'
}
),
serving_config=ServingConfig(
# rough estimate for the engines this includes model weights + kv cache + overhead + intermediate states
Expand All @@ -30,6 +33,9 @@
model="fixie-ai/ultravox-v0_4",
trust_remote_code=True,
guided_decoding_backend="outlines",
library_overrides={
"vllm": 'vllm[audio]==0.6.0'
}
),
serving_config=ServingConfig(
# rough estimate for the engines this includes model weights + kv cache + overhead + intermediate states
Expand Down

0 comments on commit 6696c5f

Please sign in to comment.