[Core] Consolidate prompt arguments to LLM engines (#4328)

Co-authored-by: Roger Wang <ywang@roblox.com>
2024-05-29 04:29:31 +08:00
parent 290f4ada2b
commit 5ae5ed1e60
43 changed files with 1407 additions and 442 deletions
--- a/tests/tokenization/test_detokenize.py
+++ b/tests/tokenization/test_detokenize.py
@@ -123,8 +123,11 @@ def create_sequence(prompt_token_ids=None):
    prompt_token_ids = prompt_token_ids or [1]
    return Sequence(
        seq_id=0,
-        prompt="<s>",
-        prompt_token_ids=prompt_token_ids,
+        inputs={
+            "prompt": "<s>",
+            "prompt_token_ids": prompt_token_ids,
+            "multi_modal_data": None,
+        },
        block_size=16,
    )