GPU Taskman shows per-process VRAM and an LLM weight and KV split
MIT-licensed GPU Taskman v0.3.3, released 7 November 2026, reports per-process VRAM and estimates LLM weights and KV cache.
Wildness 2/5 · Mostly tamed
Topic · 5 stories
mit
5 stories tagged mit on AI Tamer, newest first.
Reading a license before you vendor code
Vendoring copies someone else's source into your repository. The license sets what you may do and what you must keep. This post covers where to look and what MIT and Apache 2.0 require.
Wildness 1/5 · TamedEarendil Pi 1.0: MIT coding-agent harness with Codemode, MCP, and experimental Durable
Earendil ships Pi 1.0—MIT hardened minimal coding-agent harness with Codemode (native MCP), deferred tools, virtual models, Anthropic cache warming, and fullscreen TUI. Same-day experimental Pi Durable.
Wildness 4/5 · Still wildNaive-N0.5-Flash: MIT 309B MoE (15.5B active), native 1M context
NaiveAI’s Naive-N0.5-Flash (Sep 27, 2026): open-weight 309B MoE / 15.5B active, native 1M hybrid SWA–DSA, MIT on HF. API ($0.10/$0.40/$0.01) and NaiveRT remain future-tense—NaiveRT GitHub still 404 at the time of writing (promised by Oct 12). Benches/tok/s are NaiveAI harness claims only.
Wildness 5/5 · WildPerplexity pplx-embed-v2-context-9b-preview: MIT contextual RAG embeddings (preview)
Perplexity published open-weight pplx-embed-v2-context-9b-preview on Hugging Face (MIT): contextual chunk embeddings for RAG. Preview may break; not on Perplexity API yet. Use encode_queries vs encode; int8 + MRL 1024/2048; transformers≥5.4 + trust_remote_code.
