sm121

Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)

Measured SM121 compatibility recipe for MiniMax H3 FL2VA on one NVIDIA DGX Spark with vLLM-Omni and online FP8.

DGX Spark research and tests - containers, benchmarks, and investigation notes for running models on GB10 (SM 12.1)

7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data validator, training, and merge.

Optimized CUDA kernels for NVIDIA GB10 Blackwell (sm_121, DGX Spark). RMSNorm + GELU. First sm_121 kernel on HuggingFace Kernel Hub.

DeepSeek-V4-Flash DSpark speculative decoding on 2x DGX Spark (GB10/sm_121), 1M context — our fp8 recipe + independent reproduction and cross-build benchmarks of the NVFP4-KV build. Honest, apples-to-apples measurements.

Production runbook for Qwen3.5-122B hybrid INT4+FP8 on NVIDIA DGX Spark GB10 — optimization stack, PD firmware wedge diagnosis, bench results

Qwen3.8-Flash-Next as Cogni-Brain on NVIDIA DGX Spark (GB10): HashK GPU PLE + SGLang NEXTN, 36.8 tok/s code, 100/100 tool-eval, 262K context.

Patches + recipe to deploy festr2/MiMo-V2.5-Pro-NVFP4-MXFP8-attn-TP8 on 8-node DGX Spark sm_121 (Ray + vLLM, TP=8). Fixes the fused-qkv loader bug that mis-slotted Q values as K/V on 7 of 8 ranks.

Optimized SM121 vLLM container and benchmark report for nvidia/diffusiongemma-26B-A4B-it-NVFP4

Pre-built PyTorch wheels and build scripts for NVIDIA DGX Spark (GB10, sm_121, Blackwell, CUDA 13.0, ARM64)

Empirical kernel scheduling characterization for NVIDIA GB10 (SM121a). Sweeps GEMM tile configurations, classifies PTX instruction paths, captures hardware telemetry

Ornith-1.5-35B NVFP4-W4A16 + BF16 MTP via SGLang on SM12X (SM120/SM121). Click-run serve + SM12X-LLM-BENCH claim row.

DGX Spark (GB10/SM121) platform support for Meta's KernelAgent — auto-detect, hardware constraints, safe Triton configs

Measured vLLM serving for 1–2 NVIDIA DGX Spark (GB10): TP=2 RoCE flagship, validation ledger, stranger-ready Path A/B onboarding.

Docker Compose setup for ComfyUI on NVIDIA DGX Spark (GB10/sm_121) — NGC base image, patched xformers, self-compiled SageAttention, non-root execution

Measured GLM-5.2-Vision NVFP4 reproduction on 8x DGX Spark: 1M context, native SM121, c1/c8 throughput, and fresh 60-minute stability.

Complete GB10 (DGX Spark, sm_121) block-FP8 Triton kernel configs for DeepSeek-V4-Flash-0731 at TP=2, including the DSpark main_proj shape missing from every earlier run

Reproducible TP=2 deployment, container build, and experiment report for DeepSeek V4 Flash on two DGX Sparks

LLM serving engine for NVIDIA DGX Spark (GB10/sm_121) with Bayesian auto-tuning