TCM-Serve applies modality-aware scheduling to reduce average TTFT by 54% and 78.5% for latency-critical requests in MLLM inference.
Inf-mllm: Efficient streaming inference of multimodal large language models on a single gpu, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TCM-Serve: Modality-aware Scheduling for Multimodal Large Language Model Inference
TCM-Serve applies modality-aware scheduling to reduce average TTFT by 54% and 78.5% for latency-critical requests in MLLM inference.