biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build][Bugfix] Ensure compatibility with transformers 4.52 (#18678)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-06-04 19:49:20 +08:00
committed by GitHub
parent 35cf32df30
commit 01dc9a76db
13 changed files with 82 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/models/multimodal/generation/test_granite_speech.py
View File

@@ -29,7 +29,7 @@ def vllm_to_hf_output(
return output_ids, hf_output_str, out_logprobs
MODEL_NAME = "ibm-granite/granite-speech-3.3-8b"
MODEL_NAME = "ibm-granite/granite-speech-3.3-2b"
# Audio lora co-exists directly in the model directory, but
# currently still needs to be passed directly to vLLM.
audio_lora_path = MODEL_NAME