popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: wrap up completed story metadata

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-14 17:09:04 +03:00
parent 22467f145c
commit 7b3399760e
5 changed files with 81 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.scratch/dashboard-test-runner/PRD.md
View File

@@ -12,4 +12,10 @@ Provide an opt-in, admin-only tracker Dashboard Testing tab that dynamically dis
- One active run. - One active run.
- Real inference stays separately environment-gated and excluded from default suites. - Real inference stays separately environment-gated and excluded from default suites.
## Operator workflow
See [`docs/dev/dashboard-test-runner.md`](../../docs/dev/dashboard-test-runner.md)
for launch configuration, default safe suites vs the gated real-inference suite,
and required environment variables.
See `prd.json` for executable Ralph user stories and acceptance criteria. See `prd.json` for executable Ralph user stories and acceptance criteria.

7
.scratch/dashboard-test-runner/prd.json
View File

@@ -51,15 +51,16 @@
"uv run pytest tests/test_dashboard.py tests/test_dynamic_routing.py -q passes." "uv run pytest tests/test_dashboard.py tests/test_dynamic_routing.py -q passes."
], ],
"priority": 3, "priority": 3,
"passes": false, "passes": true,
"notes": "Do not reintroduce --enable-test-runner without implementing its CLI argument in US-001.", "notes": "Do not reintroduce --enable-test-runner without implementing its CLI argument in US-001.",
"dependsOn": [ "dependsOn": [
"US-001", "US-001",
"US-002" "US-002"
] ],
"completionNotes": "Completed by agent"
} }
], ],
"metadata": { "metadata": {
"updatedAt": "2026-07-11T17:02:30.520Z" "updatedAt": "2026-07-12T01:58:06.286Z"
} }
} }

65
.scratch/distributed-inference-performance/prd.json
View File

@@ -16,8 +16,9 @@
], ],
"priority": 1, "priority": 1,
"passes": true, "passes": true,
"notes": "Completed 2026-07-14. Deterministic direct/relay and cached/stateless stub benchmark with JSON/summary attribution; focused test suite passes (7). Source issue: .scratch/distributed-inference-performance/issues/01-baseline-profiling-harness.md", "notes": "Source issue: .scratch/distributed-inference-performance/issues/01-baseline-profiling-harness.md",
"dependsOn": [] "dependsOn": [],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "DIP-002", "id": "DIP-002",
@@ -31,9 +32,12 @@
"Tests cover binary, JSON, timeout, disconnect, cancellation, and cleanup" "Tests cover binary, JSON, timeout, disconnect, cancellation, and cleanup"
], ],
"priority": 2, "priority": 2,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/distributed-inference-performance/issues/02-relay-session-compatibility.md", "notes": "Source issue: .scratch/distributed-inference-performance/issues/02-relay-session-compatibility.md",
"dependsOn": ["DIP-001"] "dependsOn": [
"DIP-001"
],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "DIP-003", "id": "DIP-003",
@@ -47,9 +51,12 @@
"Benchmark shows healthy-session connection count independent of token count" "Benchmark shows healthy-session connection count independent of token count"
], ],
"priority": 3, "priority": 3,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/distributed-inference-performance/issues/03-http-keepalive.md", "notes": "Source issue: .scratch/distributed-inference-performance/issues/03-http-keepalive.md",
"dependsOn": ["DIP-001"] "dependsOn": [
"DIP-001"
],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "DIP-004", "id": "DIP-004",
@@ -63,9 +70,12 @@
"Tests verify cadence and cleanup" "Tests verify cadence and cleanup"
], ],
"priority": 4, "priority": 4,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/distributed-inference-performance/issues/04-seam-telemetry.md", "notes": "Source issue: .scratch/distributed-inference-performance/issues/04-seam-telemetry.md",
"dependsOn": ["DIP-001"] "dependsOn": [
"DIP-001"
],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "DIP-005", "id": "DIP-005",
@@ -79,9 +89,12 @@
"Tests cover compressible, incompressible, threshold, malformed, and legacy bodies" "Tests cover compressible, incompressible, threshold, malformed, and legacy bodies"
], ],
"priority": 5, "priority": 5,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/distributed-inference-performance/issues/05-adaptive-compression.md", "notes": "Source issue: .scratch/distributed-inference-performance/issues/05-adaptive-compression.md",
"dependsOn": ["DIP-001"] "dependsOn": [
"DIP-001"
],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "DIP-006", "id": "DIP-006",
@@ -95,9 +108,12 @@
"Wire and token-output regression tests pass" "Wire and token-output regression tests pass"
], ],
"priority": 6, "priority": 6,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/distributed-inference-performance/issues/06-activation-framing-copies.md", "notes": "Source issue: .scratch/distributed-inference-performance/issues/06-activation-framing-copies.md",
"dependsOn": ["DIP-001"] "dependsOn": [
"DIP-001"
],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "DIP-007", "id": "DIP-007",
@@ -111,9 +127,13 @@
"Tests cover chunking, slow consumers, failure, and legacy peers" "Tests cover chunking, slow consumers, failure, and legacy peers"
], ],
"priority": 7, "priority": 7,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/distributed-inference-performance/issues/07-prefill-backpressure.md", "notes": "Source issue: .scratch/distributed-inference-performance/issues/07-prefill-backpressure.md",
"dependsOn": ["DIP-001", "DIP-004"] "dependsOn": [
"DIP-001",
"DIP-004"
],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "DIP-008", "id": "DIP-008",
@@ -127,9 +147,20 @@
"Gate verifies token identity, session stability, and resource cleanup" "Gate verifies token identity, session stability, and resource cleanup"
], ],
"priority": 8, "priority": 8,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/distributed-inference-performance/issues/08-end-to-end-performance-gate.md", "notes": "Source issue: .scratch/distributed-inference-performance/issues/08-end-to-end-performance-gate.md",
"dependsOn": ["DIP-002", "DIP-003", "DIP-004", "DIP-005", "DIP-006", "DIP-007"] "dependsOn": [
"DIP-002",
"DIP-003",
"DIP-004",
"DIP-005",
"DIP-006",
"DIP-007"
],
"completionNotes": "Completed by agent"
}
],
"metadata": {
"updatedAt": "2026-07-12T02:35:28.752Z"
} }
]
} }

22
.scratch/node-capability-admission/prd.json
View File

@@ -35,11 +35,12 @@
"Full pytest passes or an exact unrelated blocker is recorded" "Full pytest passes or an exact unrelated blocker is recorded"
], ],
"priority": 2, "priority": 2,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/node-capability-admission/issues/02-doctor-real-forward.md", "notes": "Source issue: .scratch/node-capability-admission/issues/02-doctor-real-forward.md",
"dependsOn": [ "dependsOn": [
"NCA-001" "NCA-001"
] ],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "NCA-003", "id": "NCA-003",
@@ -54,12 +55,13 @@
"Full pytest passes or an exact unrelated blocker is recorded" "Full pytest passes or an exact unrelated blocker is recorded"
], ],
"priority": 3, "priority": 3,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/node-capability-admission/issues/03-fail-closed-startup-admission.md", "notes": "Source issue: .scratch/node-capability-admission/issues/03-fail-closed-startup-admission.md",
"dependsOn": [ "dependsOn": [
"NCA-001", "NCA-001",
"NCA-002" "NCA-002"
] ],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "NCA-004", "id": "NCA-004",
@@ -76,12 +78,13 @@
"Full pytest passes or an exact unrelated blocker is recorded" "Full pytest passes or an exact unrelated blocker is recorded"
], ],
"priority": 4, "priority": 4,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/node-capability-admission/issues/04-tracker-validated-capability-routing.md", "notes": "Source issue: .scratch/node-capability-admission/issues/04-tracker-validated-capability-routing.md",
"dependsOn": [ "dependsOn": [
"NCA-001", "NCA-001",
"NCA-003" "NCA-003"
] ],
"completionNotes": "Completed by agent"
}, },
{ {
"id": "NCA-005", "id": "NCA-005",
@@ -96,15 +99,16 @@
"Full pytest passes or an exact unrelated blocker is recorded" "Full pytest passes or an exact unrelated blocker is recorded"
], ],
"priority": 5, "priority": 5,
"passes": false, "passes": true,
"notes": "Source issue: .scratch/node-capability-admission/issues/05-docs-hardware-lane-contract.md", "notes": "Source issue: .scratch/node-capability-admission/issues/05-docs-hardware-lane-contract.md",
"dependsOn": [ "dependsOn": [
"NCA-002", "NCA-002",
"NCA-004" "NCA-004"
] ],
"completionNotes": "Completed by agent"
} }
], ],
"metadata": { "metadata": {
"updatedAt": "2026-07-11T19:16:52.768Z" "updatedAt": "2026-07-12T01:54:03.030Z"
} }
} }

21
docs/issues/42-gguf-llamacpp-node-backend.md
View File

@@ -1,9 +1,16 @@
# US-042 — GGUF/llama.cpp node backend # US-042 — GGUF/llama.cpp node backend
Status: planned Status: planned
Priority: High (whole-model GGUF shortcut; distributed path in [ADR-0024](../adr/0024-distributed-gguf-runtime.md)) Priority: High (unlocks DeepSeek-V4-Flash on volunteer hardware — the pool's core value)
Stage: Draft design Stage: Draft design
## Goal
Run **DeepSeek-V4-Flash** as the first real large-model target on volunteer
hardware via GGUF/llama.cpp. This epic is no longer GLM-oriented: the initial
objective is to prove that DeepSeek-V4-Flash can load and serve correctly on
consumer/unified-memory nodes, then expand from there.
## Context ## Context
The node backend is transformers-only (`model_backend.py` → The node backend is transformers-only (`model_backend.py` →
@@ -35,17 +42,7 @@ to it (single-hop route). Smallest step, no cross-node activation work, and
already useful: Strix Halo 128 GB serves DeepSeek-V4-Flash IQ3_XXS (114 GB) already useful: Strix Halo 128 GB serves DeepSeek-V4-Flash IQ3_XXS (114 GB)
via llama.cpp Vulkan today. via llama.cpp Vulkan today.
Recommended sequencing: **C first** (US-042), then **ADR-0024 benchmark gate** (DGR-001), then distributed native worker (DGR-002+). Direction B (llama.cpp RPC) is rejected per ADR-0024. Recommended sequencing: C first (small, real value), then A/B investigation.
## Runtime sequencing
| Stage | Track | Delivers |
|---|---|---|
| **C — Whole-model GGUF** | US-042 (this issue) | Single-hop llama.cpp, billing, relay streaming |
| **0 — Benchmark gate** | ADR-0024 DGR-001 | Safetensors vs GGUF measured contract |
| **1 — Distributed GGUF** | ADR-0024 `.scratch/distributed-gguf-runtime/` | gRPC C++ worker, layer-range GGUF |
Phase C uses the existing tracker hop path (whole model, one node). ADR-0024 direction A (layer-range GGUF + activations) merges into the native worker track after the benchmark gate — not in parallel with phase C on the same backend without an integration plan.
## Also in scope ## Also in scope