popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
106 Commits 4 Branches 0 Tags
ac053f5800a43fabe3d4301a67b87958ca02482f
Commit Graph

12 Commits

Author SHA1 Message Date
Dobromir Popov
c5c60cf289 Merge branch 'master' of https://git.d-popov.com/popov/neuron-tai 2026-07-01 14:45:13 +03:00
Dobromir Popov
d1e75ddded docs: consolidate all docs under docs/ — single source of truth 
Move issues (01–29) and PRD from .scratch/distributed-inference-network/
into docs/issues/ and docs/. Update ralph_progress.py DEFAULT_PRD path
and rewrite docs/agents/issue-tracker.md to reflect the new layout.

The distributed_inference_network.egg-info/docs/ mirror is a build
artifact already covered by *.egg-info/ in .gitignore — not committed.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-07-01 14:18:26 +03:00
Dobromir Popov
2b439e8a5f docs: add US-020–029 issue files, ADR 0011–0014, update prd.json to 29/29 
Issue files (.scratch/issues/20-29): retrospective specs for all work
done in the current sprint — hardening, route-timeout, start-layer
protocol, heartbeat stats, availability map, rolling RPM, smart
assignment, throughput routing, routing tests, relay outbound client.

ADRs (docs/adr/0011-0014):
  0011 — Auto-shard from memory budget and tracker network assignment
  0012 — X-Meshnet-Start-Layer overlapping shard execution protocol
  0013 — Rolling RPM statistics, smart assignment scoring, throughput routing
  0014 — Relay outbound client for NAT/internet pipeline hops

prd.json: US-020 through US-029 added, all marked done. ralph_progress.py
now shows 29/29 complete (100%).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-30 22:15:41 +03:00
Dobromir Popov
be37048145 feat(us-018): WSL2 install guide, two-machine LAN test docs, and test script 
- docs/INSTALL_WINDOWS.md: step-by-step WSL2 + CUDA + meshnet-node install on
  Windows 11, including port-proxy setup and known issues
- docs/TWO_MACHINE_TEST.md: two-machine LAN test procedure, start order,
  verification steps, latency reading, and Known Issues section
- scripts/test_lan_inference.py: stdlib-only test script; sends 3 chat
  completions, validates OpenAI response format, prints tokens + latency,
  exits 0 on success; auto-discovers gateway from tracker if --gateway omitted

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-30 01:37:33 +03:00
Dobromir Popov
1bdfce657d inference working 2026-06-29 23:54:35 +03:00
Dobromir Popov
cd9e3686a5 docs(adr-0002): lock TAI tokenomics — 1B supply, revenue-backed, 90% floor 
Locked decisions:
- 1 billion TAI hard cap, no minting, halving-style emission decay
- No transfer tax; spread-only revenue, decreases with volume
- Buyback floor = 90% of current organic backing price (ratcheting up)
- Wind-down guarantee: 90% floor always funded by protocol spread
- Post-listing speculative risk acknowledged and accepted
- Node bootstrap: probationary period = stake-free entry (no loan/grant)
- Listing threshold (provisional): $50k volume AND 25 nodes / 15+ operators

Open parameters noted: halving schedule, dynamic spread curve, listing %, legal.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-29 15:34:15 +03:00
Dobromir Popov
202b579bd1 docs(adr-0002): rewrite TAI tokenomics with revenue-backed model 
- Token named TAI, fixed supply (BTC-inspired), no open market during bootstrap
- Price anchored to inference revenue: team holds ~100% → 36% over ~5 years
- 95% soft buyback floor; ~10% protocol spread funds wind-down reserve
- Wind-down guarantee: protocol can always buy back all issued TAI at issue price
- Open questions section captures unresolved parameters for token launch

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-29 15:15:15 +03:00
Dobromir Popov
b02e07d308 docs: add ADRs and user stories for real model inference stack (US-011–014) 
ADR-0008: binary activation wire format — raw bfloat16 over HTTP, zstd compression,
128-token chunked prefill; replaces base64 JSON (~33% overhead removed).

ADR-0009: coverage-first shard assignment and tracker-as-first-layer-node —
any node serving layers[0..k] becomes the inference entry point for that model;
bin-packing fills all coverage gaps before adding redundancy; tracker issues
LOAD_SHARD/DROP_SHARD rebalance directives; nodes declare VRAM + quantization.

US-011: binary wire format migration
US-012: real PyTorch layer execution (transformers + bitsandbytes, test on GPT-2)
US-013: coverage-first tracker bin-packing with VRAM-aware shard assignment
US-014: tracker-as-node (tracker node serves first layers + handles client requests)

CONTEXT.md: Tracker Node, Coverage Map, Rebalance Directive terms added.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-06-29 14:43:54 +03:00
Dobromir Popov
a2aa22fc08 docs: clarify validation slash model 2026-06-29 02:47:36 +03:00
Dobromir Popov
8900990193 docs: clarify contract boundary 2026-06-29 02:31:23 +03:00
Dobromir Popov
2f1f9717be tasks 2026-06-29 00:10:21 +03:00
Dobromir Popov
0f24a1d4f9 iinit 2026-06-28 23:49:11 +03:00