A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 10:45 UTC
[Bugfix] Fix Token IDs Reference for MiniCPM-V When Images are Provided With No Placeholders (#8991)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Alex Brooks committed
Oct 1, 2024 at 03:52 UTC
1fe0a4264aa94ceeccc7e8d99ac0d72f0560f541
1 file changed
+1
-1
vllm/model_executor/models/minicpmv.py
+1
-1
@@ -274,8 +274,8 @@ def input_processor_for_minicpmv(ctx: InputContext, llm_inputs: LLMInputs):
274
get_slice_image_placeholder(image_size, num_image)
275
276
prompt = llm_inputs.get("prompt")
277
+ token_ids = llm_inputs.get("prompt_token_ids")
278
if prompt is None:
278
- token_ids = llm_inputs.get("prompt_token_ids")
279
prompt = tokenizer.decode(token_ids)
280
281
pattern = "(<image>./</image>)"