BWhat changed
Integrated DeepSpeed-MII/Inference with Dynamic SplitFuse to compose prompt and decoding work into better-balanced forward passes for throughput/latency tradeoffs.
Scientific scope
Integrated DeepSpeed-MII/Inference with Dynamic SplitFuse to compose prompt and decoding work into better-balanced forward passes for throughput/latency tradeoffs. Inherits Orca/PagedAttention/DeepSpeed and chunked scheduling ideas. Distinct from NVIDIA's diffusion FastGen. Workload/hardware-dependent throughput curves are not a universal speed claim or proof of an optimal production scheduler.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits Orca/PagedAttention/DeepSpeed and chunked scheduling ideas. Distinct from NVIDIA's diffusion FastGen. Workload/hardware-dependent throughput curves are not a universal speed claim or proof of an optimal production scheduler.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction