DeepSeek-V4-Flash-DSpark-v026-SM121

(★ 30)

DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)

Owner Repos

hermes-concurrent-agents ★ 79

Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordinated, crash-recovering.

Python
hermes-buzz-shared-profile ★ 52

macOS Hermes skill for sharing one canonical writable profile across Buzz and ACP surfaces

Python
llm-wiki_obsidian_hermes_r0b0tlabbra1n ★ 30

Filesystem-first LLM-Wiki + Obsidian + Hermes Agent memory system. Markdown source of truth, SQLite FTS5 search, secret scanning, tier-based memory. Built for local LLM setups.

Python
qwen38-27b-nvfp4-sm121-vllm ★ 26

Qwen3.8-27B NVFP4 (W4A16 shipped recipe) + MTP on NVIDIA DGX Spark GB10/SM121 — vLLM v0.27.2rc0, FP8 KV, 262K context, full reproducibility pack

Python
qwen38-27b-nvfp4-sm121-sglang ★ 19

Qwen3.8-27B NVFP4 on SGLang (DGX Spark / SM121): official image pin, native DSpark/EAGLE click-run, matched evals

Python
minimax-m27-nvfp4-gb10-benchmark ★ 13

MiniMax M2.7 NVFP4 dual-GB10 Blackwell benchmark: vLLM FlashInfer-CUTLASS, public data, HTML canvas report, and Docker runtime.

HTML

File Explorer

ZIP Download
  • .gitignore
  • AGENTS.md
  • CONTAINER.md
  • LICENSE
  • NOTICE
  • README.md
  • THIRD_PARTY_NOTICES.md

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Link
Example

Command Glossary

Commands referenced in this DOCs, explained below.

🔍

docker pull

View Details ▼

This command is an alias of `docker image pull`.

tldr docker image pull

View documentation for the original command:

🔍

python3

View Details ▼

This command is an alias of `python`.

tldr python

View documentation for the original command:

// repository documentation