What is recorded here?
Integrated DeepSpeed-MII/Inference with Dynamic SplitFuse to compose prompt and decoding work into better-balanced forward passes for throughput/latency tradeoffs.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
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.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Connor Holmes; Masahiro Tanaka; Michael Wyatt; Ammar Ahmad Awan; Jeff Rasley; Samyam Rajbhandari; Reza Yazdani Aminabadi; Heyang Qin; Arash Bakhtiari; Lev Kurilenko; Yuxiong He
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.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
DeepSpeed-FastGen: Dynamic SplitFuse prompt/decode scheduling
Integrated DeepSpeed-MII/Inference with Dynamic SplitFuse to compose prompt and decoding work into better-balanced forward passes for throughput/latency tradeoffs.
Scientific scope
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.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Connor Holmes; Masahiro Tanaka; Michael Wyatt; Ammar Ahmad Awan; Jeff Rasley; Samyam Rajbhandari; Reza Yazdani Aminabadi; Heyang Qin; Arash Bakhtiari; Lev Kurilenko; Yuxiong He
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.