p150 ETH-dispatch compliance (2026-10-05): default ETH dispatch, 1 CQ, 12x10 in Python API and server; numbers re-measured

Python API: warm-up so the first real call is fast (warmup_variants, model.warmup()), quiet logs, install extras

Python API (2026-10-04): pip install -e code/, from_pretrained() + model(...), Python-first quickstart

Optimized build (2026-10-03): v3: 115 ms e2e, 8.3 ms/token decode

Update README.md

Optimized build v2 (2026-10-03): 149 ms e2e, 1.15x faster than RTX 5090 bf16

Optimized build (2026-10-03): vision/prefill/decode speedups on a 12x10 grid with ETH dispatch

Card: RTX 5090 comparison row + caveat

Card: simplify the generated quickstart paragraph

Restore card metadata (license, pipeline_tag, tags)

Add files using upload-large-folder tool

Card: simplify the generated quickstart paragraph

Restore card metadata (license, pipeline_tag, tags)

Add files using upload-large-folder tool

Upload README.md with huggingface_hub

Restore license, pipeline_tag, base_model and descriptive tags after tt-model push

Add files using upload-large-folder tool

Restore license, pipeline_tag, base_model and descriptive tags after tt-model push

Add files using upload-large-folder tool

Add Tenstorrent Blackhole tt-nn port