arXiv (OAI Expanded)
open access
Affinity-Aware Sharding for Delayed Tensor Parallelism
Delayed Tensor Parallelism (DTP) removes the blocking all-reduce of tensor-parallel Transformer inference. Every device adds its own partial output to its residual stream (and broadcasts it) immediately, but only gathers (receives) the other devices' partials $δ$ modules later. A TP to DTP change th
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Affinity-Aware Sharding for Delayed Tensor Parallelism#919373
- Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery#1064524
- Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving#660783
- Interpretable multi-omics integration across mixed-order tensors with MANTRA.#645361
- Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache#1084925
Record · ID 1083341
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive