Unverified50% confidenceFactExact time
On the DGX Spark, the official Quick Start uses vllm/vllm-openai:v0.32.0, with key parameters including --max-num-seqs 1, --gpu-memory-utilization 0.75, speculative decoding with the LiLiCorr drafter configured with 7 draft tokens, and --reasoning-parser nemotron_v3.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedNemotron 3.5 Bolt comes with a LiLiCorr drafter for speculative decoding, implemented via DFlash, with 7 speculative tokens by default in the vLLM configuration.70% similarUnverifiedThe DGX Spark (GB10) has 128 GB of unified memory and can run Nemotron 3.5 Super VL using the official NVFP4 + vLLM + LiLiCorr drafter.70% similarUnverifiedThe key decisions for running Muse Spark include the quantization scheme (FP8/INT8/4-bit), the inference framework (vLLM, TensorRT-LLM, SGLang), and the parallelism strategy (Tensor Parallel, Pipeline Parallel).67% similarUnverifiedvLLM v0.29.0 added support for models including Hy4-preview, Qwen3.8-Flash-Next, GraniteSWA, and NemotronH Omni Reasoning V3.67% similarUnverifiedvLLM configuration parameters include --tensor-parallel-size (tensor parallelism degree), --gpu-memory-utilization (GPU memory usage ratio cap), --max-num-batched-tokens (maximum number of batched tokens), and others.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049458API
curl https://kongchang.com/api/v1/knowledge/claims/1049458MCP
get_claim(id=1049458)