Spark Bench

DeepSeek V4 Flash Vision-Exp on the Anemll DSpark vLLM runtime, two Sparks (TP=2), thinking off

2× DGX Spark · vLLM (Anemll DSpark 0.1.1) ·

Tested configuration

Hardware
2x NVIDIA DGX Spark (128GB each)
Serving runtime
vLLM (Anemll DSpark 0.1.1)
Runtime version or build
the recipe's Anemll dspark-vllm-gx10 0.1.1 runtime, built locally from Anemll/dspark-vllm-gx10 v0.1.1 (47503f8e38da): upstream vLLM 752a3a504485 (docker/Dockerfile --target vllm-openai, torch_cuda_arch_list=12.1a), then the Anemll runtime layer (FlashInfer 0472b9b3f2fb, b12x 7dc6fb8fcc64, CUTLASS DSL 4.5.2). The prebuilt ghcr.io/anemll/dspark-vllm-gx10:0.1.1 image was not used.
Weight quantization or precision
Unavailable
Benchmark date
Recipe credit
MiaAI-Lab DeepSeek-v4-Flash DSpark 2x recipeBy MiaAI-Laba8b4636710068fd30edb98e1365d567086cc208e

Decode sweep

~256 input / 512 output tokens per request. Output throughput is aggregate across concurrent requests. TTFT means time to first token.

ConcurrencyOutput tok/sTTFT p95 (s)
125.930.69
247.040.76
465.241.01
879.9126.29
1274.8345.51
1678.1581.35

Prefill and context

Configured request window
1,048,576 tokens
Longest tested prompt
245,760 target input tokens
Validated retrieval
≈240K input tokens · passkey passed

Input throughput uses full request wall time. The passkey measures retrieval from one long prompt.

Workload (c1)Input tok/sTTFT p95 (s)
4,096 input tokens722.553.78
32,768 input tokens1,334.3023.04
131,072 input tokens1,150.22111.94
245,760 input tokensPasskey prompt1,325.83185.15

Sustained load

20-minute soak at concurrency 8 · ~1024 input / 512 output tokens per request.

Aggregate throughput
84.53 output tok/s
TTFT p95
23.27 s
Completed requests
205
Request errors
0

Serving regression checks 13/13 passed

Tool-use evaluation

Complete · 100% completionSafety gate failed

Compare only against complete results with 100% completion under the same protocol ID.

Protocol ID
tool-eval-standard-v1-b60e2f0
Workload
69 mock-tool scenarios per trial · 3 trials
Mean score
91.7 / 100
Pass@3 · passed at least once
94.2%
Pass³ · passed every trial
84.1%

Read the tool-eval report and scenario findings