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

feat: MAINT-002 - Update evidence READMEs for all completed stories

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-14 14:23:27 +03:00
parent 454a681a50
commit 64f83d4392
2 changed files with 17 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
.scratch/distributed-gguf-runtime/evidence/DGR-005/README.md
View File

@@ -7,20 +7,23 @@ real-model integration (TinyLlama 1.1B, opt-in via MESHNET_ENABLE_REAL_INFERENCE
All six acceptance criteria pass:
1. **Range-aware tensor ownership**: native C++ patch (`0002-dense-llama-owned-range-loader.patch`)
1. **Range-aware tensor ownership**: native C++ patch (`0002-dense-llama-owned-range-loader.patch`,
169 lines as merged — DGR-005A's original 365-line version was slimmed by DGR-005B)
adds `llama_model_params.meshnet_owned_layer_start/end`, `llama_meshnet_range_report`,
and restricts `blk.N.*` registration to the owned range.
2. **Head/tail embedding loading**: head loads `token_embd.weight`; tail loads `output_norm`/`output`
(with tied-embedding dedup). Middle shards load zero endpoint tensors.
3. **Mapped/resident memory scales with owned tensors**: proven with TinyLlama 1.1B Q4_K_M.
4. **Targeted pytest tests**: `tests/test_llama_cpp_dependency.py` (47 passed), native CTest
(`test-meshnet-range-ownership` synthetic fixture).
4. **Targeted pytest tests**: `tests/test_llama_cpp_dependency.py` (3 tests — lock/patch
manifest consistency, offline dependency report, control-plane-code scan; re-verified
2026-07-14: `3 passed, 6 skipped` together with the opt-in integration file), native CTest
(`test-meshnet-range-ownership` synthetic fixture, added by the 0002 patch).
5. **compileall, ruff, git diff --check, full pytest**: all pass.
6. **Integration test**: `tests/test_gguf_distributed_load.py` (6/6, opt-in real model).
## Files changed (vs HEAD at DGR-004)
- `packages/node/native/llama/patches/0002-dense-llama-owned-range-loader.patch` — 365-line native patch
- `packages/node/native/llama/patches/0002-dense-llama-owned-range-loader.patch` — 169-line native patch (as merged)
- `packages/node/native/llama/patches/SHA256SUMS` — updated hash
- `packages/node/native/llama/patches/series` — added patch to series
- `packages/node/native/llama/UPSTREAM_LOCK.json` — updated patched_tree, serial number