From a58a76783d853f8a524c9550238a4a57a0b321ec Mon Sep 17 00:00:00 2001 From: WorstDev01 Date: Tue, 10 Jun 2025 23:36:47 +0200 Subject: [PATCH] Add multimodal limit parameter support - Updated convert_limit_mm_per_prompt to handle multiple types - Added limit_mm_per_prompt parameter for image and video limits Note: Consider adjusting default values - perhaps image limit > 1 or video=1 --- src/engine_args.py | 1 + src/utils.py | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/src/engine_args.py b/src/engine_args.py index 6ed1557..d1bc532 100644 --- a/src/engine_args.py +++ b/src/engine_args.py @@ -91,6 +91,7 @@ DEFAULT_ARGS = { "disable_logprobs_during_spec_decoding": os.getenv('DISABLE_LOGPROBS_DURING_SPEC_DECODING', None), "otlp_traces_endpoint": os.getenv('OTLP_TRACES_ENDPOINT', None), "use_v2_block_manager": os.getenv('USE_V2_BLOCK_MANAGER', 'true'), + "limit_mm_per_prompt": convert_limit_mm_per_prompt(os.getenv('LIMIT_MM_PER_PROMPT', 'image=1,video=0')), } def match_vllm_args(args): diff --git a/src/utils.py b/src/utils.py index 8a66205..ee1b927 100644 --- a/src/utils.py +++ b/src/utils.py @@ -15,9 +15,14 @@ except ImportError: logging.basicConfig(level=logging.INFO) +# Updated to parse multiple comma-separated multimodal limits (e.g., 'image=1,video=0') def convert_limit_mm_per_prompt(input_string: str): - key, value = input_string.split('=') - return {key: int(value)} + result = {} + pairs = input_string.split(',') + for pair in pairs: + key, value = pair.split('=') + result[key] = int(value) + return result def count_physical_cores(): with open('/proc/cpuinfo') as f: