mr-r0b0t - r0b0tlab
- 93 followers
- United States of America
- @mr_r0b0t
Popular repositories Loading
-
hermes-concurrent-agents hermes-concurrent-agents Public
Deploy concurrent Hermes Agent workers on unified-memory GPUs (GB10, DGX Spark) for maximum total tok/s. Profile-isolated, kanban-coordinated, crash-recovering.
-
hermes-buzz-shared-profile hermes-buzz-shared-profile Public
macOS Hermes skill for sharing one canonical writable profile across Buzz and ACP surfaces
-
llm-wiki_obsidian_hermes_r0b0tlabbra1n llm-wiki_obsidian_hermes_r0b0tlabbra1n Public
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.
-
DeepSeek-V4-Flash-DSpark-v026-SM121 DeepSeek-V4-Flash-DSpark-v026-SM121 Public
DeepSeek-V4-Flash-DSpark optimized vLLM 0.26.0 SM121 dual-GB10 evidence (NVFP4 KV, B12X, DSpark K6)
-
qwen38-27b-nvfp4-sm121-vllm qwen38-27b-nvfp4-sm121-vllm Public
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
-
qwen38-27b-nvfp4-sm121-sglang qwen38-27b-nvfp4-sm121-sglang Public
Qwen3.8-27B NVFP4 on SGLang (DGX Spark / SM121): official image pin, native DSpark/EAGLE click-run, matched evals
Repositories
- qwen38-flash-next-w4a16-sm121-sglang Public
Self-quantized Qwen3.8-Flash-Next NVFP4 W4A16 served on 2x NVIDIA GB10 (SM121) with SGLang TP=2 — MTP NEXTN 2.48x c1 / 2.28x c4, strict zero-NVRM loader gate, full repro suite
- qwen38-flash-next-nvfp4-sm121-sglang Public
Click-run SGLang SM121 package for RadixArk/Qwen3.8-Flash-Next-NVFP4
- bot-hive Public
Bot Hive — bot orchestration framework: plan-gated orchestrator, lane bots, binding verification
- ornith-15-35b-nvfp4-w4a16-sm121-sglang Public
Ornith-1.5-35B NVFP4-W4A16 + BF16 MTP via SGLang on SM12X (SM120/SM121). Click-run serve + SM12X-LLM-BENCH claim row.
- atlas Public
WIP: r0b0tlab Atlas fork carrying active GB10/SM121 and Nemotron 3.5 Lightning + DSpark development; not a qualified release
- nemotron-3.5-lightning-sglang-dflash-sm121 Public
SGLang SM121 reproducibility package: NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 + official DFlash draft head
- qwen38-27b-nvfp4-sm121-vllm Public
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
- nemotron-3.5-lightning-atlas-sm121 Public
WIP: Atlas SM121 reproducibility package for NVIDIA Nemotron 3.5 Lightning NVFP4 + official DSpark K=3; not release-qualified
- qwen38-27b-nvfp4-sm121-sglang Public
Qwen3.8-27B NVFP4 on SGLang (DGX Spark / SM121): official image pin, native DSpark/EAGLE click-run, matched evals
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…