---
type: "post"
id: "spark-ds41f-1025-release-serves-deepseek-v4-1-86e402"
slug: "spark-ds41f-1025-release-serves-deepseek-v4-1-86e402"
title: "spark-ds41f-1025 release serves DeepSeek V4.1 Flash on 3-4 DGX Sparks with all-TileLang kernels and faster prefill"
description: "The spark-ds41f project published draft release notes for spark-ds41f-1025, a deployment release for DeepSeek-V4.1-Flash-1017 rather than a new model version."
retrieval_nugget: "The spark-ds41f project published draft release notes for spark-ds41f-1025, a deployment release for DeepSeek-V4.1-Flash-1017 rather than a new model version."
published_at: "2026-10-25"
updated_at: "2026-10-25"
record_date: "2026-10-25"
date_kind: "published_at"
topics: ["inference","local-models","ai-infrastructure"]
entities: ["spark-ds41f","DeepSeek-V4.1-Flash-1017","TileLang","vLLM","DGX Spark","DeepSeek"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Adds a TileLang-based deployment release serving DeepSeek V4.1 Flash across 3–4 DGX Sparks, with all-TileLang kernels and faster prefill."
prior_refs: ["memory:eb27678d-1635-8fbf-a995-67cecf7d972b","memory:4c416acd-47a0-818c-af99-bc98dd032139"]
source_url: "https://github.com/christopherowen/spark-ds41f/blob/main/experiments/2026-10-25-spark-ds41f-candidate/release-notes.md"
source_urls: ["https://github.com/christopherowen/spark-ds41f/blob/main/experiments/2026-10-25-spark-ds41f-candidate/release-notes.md"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:spark-ds41f-1025-release-serves-deepseek-v4-1-86e402"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/spark-ds41f-1025-release-serves-deepseek-v4-1-86e402/","markdown":"https://newruntime.com/posts/spark-ds41f-1025-release-serves-deepseek-v4-1-86e402.md","json":"https://newruntime.com/posts/spark-ds41f-1025-release-serves-deepseek-v4-1-86e402.json"}
---

# spark-ds41f-1025 release serves DeepSeek V4.1 Flash on 3-4 DGX Sparks with all-TileLang kernels and faster prefill

## Retrieval answer

The spark-ds41f project published draft release notes for spark-ds41f-1025, a deployment release for DeepSeek-V4.1-Flash-1017 rather than a new model version.

The spark-ds41f project published draft release notes for spark-ds41f-1025, a deployment release for DeepSeek-V4.1-Flash-1017 rather than a new model version. The release is for a three- or four-node DGX Spark setup and says serving kernels are now TileLang except for NCCL and a few rare-path ATen copies.

On a four-node ring, the notes report prefill gains of 11.8% to 13.9% versus spark-ds41f-1022 across 32K to 1M prompts. On a three-node triangle, they report 22.5% to 28.2% faster prefill, with 3,952 tokens per second at a 1M-token prompt. The four-node configuration reports a 16,384-token prefill budget and a vLLM startup estimate of 6,512,700 KV-cache tokens.

The release fixes a prompt_logprobs request that could bring down the engine and a speculative-decoding logprob-token-ID HTTP 500. Its test record lists 5,730 passed and 160 skipped tests, with none failed. The notes do not establish independent benchmark validation, performance on other hardware, or general availability as a supported DeepSeek serving product.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Inference](https://newruntime.com/topics/inference.md): Explore the inference topic hub.
- topic hub: [Local Models](https://newruntime.com/topics/local-models.md): Explore the local-models topic hub.
- topic hub: [Ai Infrastructure](https://newruntime.com/topics/ai-infrastructure.md): Explore the ai-infrastructure topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)