TensorRT-LLM chore: Handle qwen2audio inputs ids expansion during processing

Transformers is expanding input_ids during processing since 4.48: https://github.com/huggingface/transformers/pull/35534

Hence, it does not need to be done in TRT-LLM code anymore.

Mar 25 '25 21:03 achartier

/bot run

Mar 25 '25 21:03 achartier

PR_Github #472 [ run ] triggered by Bot

Mar 25 '25 21:03 niukuo

PR_Github #472 [ run ] completed with state FAILURE /LLM/main/L0_MergeRequest_PR pipeline #405 completed with status: 'FAILURE'

Mar 25 '25 22:03 niukuo

/bot run

Mar 25 '25 23:03 achartier

PR_Github #478 [ run ] triggered by Bot

Mar 26 '25 00:03 niukuo

PR_Github #478 [ run ] completed with state FAILURE /LLM/main/L0_MergeRequest_PR pipeline #411 completed with status: 'FAILURE'

Mar 26 '25 00:03 niukuo

/bot run

Mar 26 '25 02:03 achartier

PR_Github #497 [ run ] triggered by Bot

Mar 26 '25 02:03 niukuo

PR_Github #497 [ run ] completed with state SUCCESS /LLM/main/L0_MergeRequest_PR pipeline #429 completed with status: 'SUCCESS'

Mar 26 '25 06:03 niukuo

/bot reuse-pipeline

Mar 26 '25 06:03 QiJune

PR_Github #530 [ reuse-pipeline ] triggered by Bot

Mar 26 '25 06:03 niukuo

PR_Github #530 [ reuse-pipeline ] completed with state SUCCESS Reusing PR_Github #497 for commit 5a91aab

Mar 26 '25 06:03 niukuo