Eliminating Nondeterminism in LLM Inference with Integer-Only Arithmetic
A paper titled "Eliminating Nondeterminism in LLM Inference with Integer-Only Arithmetic" appeared in the input set of arXiv announcements. The accompanying arXiv entries are two separate systems papers: Superfluid, which describes running large language models on local devices to keep data private, remove per-token cost, cut network latency, and support distributed inference, and VelServe, which addresses decode jitter in interactive LLM services so that latency SLOs for time to first token and time between tokens can be met. No abstract or detail from the nondeterminism paper itself is present, so the specific method and results it reports are not stated. The only indication of progress is the arXiv listing itself.
How this story unfolded
Key points5 items Model summary · ordered by when the evidence was published
- Point 01 11/14, 00:32
A paper titled "Eliminating Nondeterminism in LLM Inference with Integer-Only Arithmetic" appears in the arXiv announcement set.
Based on 1 - Point 02 11/16, 13:00
Superfluid is described as a local AI server for distributed LLM inference.
Based on 1 - Point 03 11/16, 13:00
Running LLMs on local devices is said to keep data private, remove per-token cost, and cut network latency.
Based on 1 - Point 04 11/16, 13:00
VelServe targets decode jitter in LLM inference with tail-calibrated scheduling.
Based on 1 - Point 05 11/16, 13:00
Interactive LLM services must meet latency SLOs for time to first token and time between tokens.
Based on 1
ReportsBy publish time · newer further down
- November 14, 2026 · Sat
- November 16, 2026 · Mon
- +2d 12h
VelServe: Taming Decode Jitters in LLM Inference with Tail-Calibrated Scheduling
Original summary arXiv:2611.18392v1 Announce Type: new Abstract: Interactive LLM services must meet latency service-level objectives (SLOs) for the time to first token (TTFT) and the time between t
arXiv cs.AI Original ↗ - +2d 12h
Superfluid: Local AI Server for Distributed LLM Inference
Original summary arXiv:2611.17753v1 Announce Type: cross Abstract: Running large language models (LLMs) on local devices keeps data private, removes per-token cost, cuts network latency, and keeps
arXiv cs.CL Original ↗ - Still developing · later reports will keep extending this axis