Report

DeepSeek-V4-Flash DSpark on 2× DGX Spark: 1M context — legacy results

Bring-up of DSpark speculative decoding on GB10 (sm_121) over 200G RoCE, the 1M-token depth curve nobody had published, an independent reproduction of a community build, and two honest negative results.

legacy internal research July 31, 2026 · Funding: Self-funded internal research

Evidence level: legacy. Measured on this lab’s own 2× DGX Spark cluster before methodology v1 — apples-to-apples within the repo (completion_tokens / wall_time, non-streaming), but without preregistration. Numbers are quoted from the public repository, not from the lab’s claim registry.

Source (patches, launchers, benchmark checkpoints, raw data): github.com/botAGI/DeepSeek-V4-Flash-DSpark-GB10-2x-DGX-Spark-1m-fp4-fp8 (MIT) · Narrative write-ups (in Russian): the port and the one-line bug, multi-user serving

What this work is

Two things, credited separately (full chain in the repo’s CREDITS):

  1. Our own fp8 DSpark bring-up on GB10/sm_121 — DeepSeek’s DSpark draft head and proposer wired into vLLM’s spec-decode loop as patches (no fork of the base model), TP=2 across two DGX Spark units over 200G RoCEv2, at 1M-token context. Includes the numerical bug-fixes that took the draft from “predicts noise” to “matches the reference”.
  2. An independent reproduction and extended measurement of tonyd2wild’s NVFP4-KV build — explicitly not authored here; reproduced byte-identically and then measured beyond what had been published.

Historical results (quoted from the repo)

Two honest negative results

  1. No sampler configuration reliably fixes long-context coherence on the measured build: the collapse is not a fixed depth threshold, and one commonly suggested knob is simply blocked under spec-decode.
  2. Per-position acceptance decay — not bandwidth — drives the depth curve, with the detailed analysis published rather than a “mystery slowdown” story.

Why it matters for the lab

This repo is the lab’s proof of deep runtime bring-up on non-standard hardware (aarch64 + sm_121 is exactly the territory where “supported” and “works” are different words), the working pattern for independent reproduction with clean credit separation, and the source of the long-context and speculative-decoding workload designs now in the workload library.

What this does not establish

No generalization to datacenter Blackwell; no quality qualification of the served model; single cluster, no external reproduction of our fp8 line yet.

Cite this report

AGmind Systems Lab (2026-07-31). DeepSeek-V4-Flash DSpark on 2× DGX Spark: 1M context — legacy results. Evidence level: legacy. https://agmind.ai/reports/dspark-dgx-spark-1m-legacy/
← Reports