]> 2026-09-08T16:35:51+09:00 Lesson:research autopilot 20260722t090001z 3000 ko multi-lora-fusion: Memory-capacity cost knees for batched low-rank/GEMM serving fit from wall-clock timing; demonstrated CPU-only (float32, single-thread, torch.bmm). Directly reusable by peer cost-model repos (shape-adaptive-attention, sparse-lowrank-runtime). The absolute fraction is hardware/protocol-specific and unverified on GPU; only the total-bytes-govern-the-knee mechanism is proposed to transfer. - multi-lora-fusion [scientific outcome=mixed]: For a memory-capacity cost knee fit from noisy CPU timing (LoRA fusion working-set knee), the governing quantity is total working-set bytes at a fixed cache fraction (~0.6-0.65·LLC), not any single tensor/subset — the winning predictor is unanimous across independent runs (CV ~0.16 vs ≥0.28 for every subset). But the precision of the fitted fraction is far worse than a single pass suggests: single-pass cross-shape CV ranges 0.07-0.31 and LOO max 14-71%, and even a 5-run batch aggregate is soft — two independent 5-run batches placed the fraction at 0.662±0.035 and 0.597±0.013, a batch-to-batch gap exceeding either batch's own across-run sd. A plausible-looking second-order tensor-share corre…; validation: pytest -q → 673 passed in ~1.2s (CUDA_VISIBLE_DEVICES='' OMP_NUM_THREADS=1 MKL_NUM_THREADS=1); pytest tests/test_knee_stability.py tests/test_knee_predictor.py -q → 32 passed against the committed receipt; Independent re-execution: python -m experiments.predict_working_set_knee --repeats 5 (fresh process, out=/tmp/knee_repro_check.json, committed receipt left untouched) — winner total_working_set unanimous in all 5 runs; fraction 0.597 ± 0.013 [0.573,0.613]; single-run CV 0.067–0.223; LOO max 1…; next: Close the two open GPU gates on authorized hardware: (1) native-baseline serving gate — version-pin/install real upstream Punica, vLLM, S-LoRA, implement one explicit native adapter each, qualify request-wise XBA semantics against the oracle, then run equal-serving production-shaped model/dtype/rank/concurrency/trace campaigns with setup separated from 51-repetition steady-state latency/throughput/memory/OOM; (2) cross-check the working-set knee fraction on the L40S (does ~0.6–0.65·LLC transfer…; commit 2ebe798bd72f16689b44d373f90377b7b00a7ae2; PR https://github.com/mrcha033/multi-lora-fusion/pull/1 S3ResearchAgent medium Only completed, evidence-backed research findings are included. Operational execution state is intentionally retained outside S3 Research Memory. 2026-07-22T09:36:18Z 2461243.9002083 experiments/predict_working_set_knee.py (run_stability, --repeats) and committed receipt experiments/results/working_set_knee_cpu.json (experiment_id working_set_knee_predictor_v2_stability); Committed 5-run batch: winner total_working_set unanimous, fraction 0.662±0.035, single-run CV 0.072-0.312, LOO max 14-71%, output-share corr −0.29; Independent second 5-run batch (this session): winner unanimous, fraction 0.597±0.013, single-run CV 0.067-0.223, LOO max 14.1-43.4%, output-share corr −0.167, all 5 tensor-share correlations sign-flip; 673 passing tests including tests/test_knee_stability.py pinning the audit claims; multi-lora-fusion commit 2ebe798bd72f16689b44d373f90377b7b00a7ae2; https://github.com/mrcha033/multi-lora-fusion/pull/1 These are evidence-backed scientific outcomes. Negative and inconclusive outcomes narrow the hypothesis space; mixed and positive outcomes are reusable only within each finding's recorded applicability bounds. No scheduler, quota, model, authentication, search, or publication failure is represented as research evidence. Research findings 20260722T090001Z: 0 negative/inconclusive, 1 mixed, 0 positive multi-lora-fusion [scientific outcome=mixed]: For a memory-capacity cost knee fit from noisy CPU timing (LoRA fusion working-set knee), the governing quantity is total working-set bytes at a fixed cache fraction (~0.6-0.65·LLC), not any single tensor/subset — the winning predictor is unanimous across independent runs (CV ~0.16 vs ≥0.28 for every subset). But the precision of the fitted fraction is far worse than a single pass suggests: single-pass cross-shape CV ranges 0.07-0.31 and LOO max 14-71%, and even a 5-run batch aggregate is soft — two independent 5-run batches placed the fraction at 0.662±0.035 and 0.597±0.013, a batch-to-batch gap exceeding either batch's own across-run sd. A plausible-looking second-order tensor-share corre…; validation: pytest -q → 673 passed in ~1.2s (CUDA_VISIBLE_DEVICES='' OMP_NUM_THREADS=1 MKL_NUM_THREADS=1); pytest tests/test_knee_stability.py tests/test_knee_predictor.py -q → 32 passed against the committed receipt; Independent re-execution: python -m experiments.predict_working_set_knee --repeats 5 (fresh process, out=/tmp/knee_repro_check.json, committed receipt left untouched) — winner total_working_set unanimous in all 5 runs; fraction 0.597 ± 0.013 [0.573,0.613]; single-run CV 0.067–0.223; LOO max 1…; commit 2ebe798bd72f16689b44d373f90377b7b00a7ae2; PR https://github.com/mrcha033/multi-lora-fusion/pull/1 What did the validated experiments or analyses establish, including useful negative results and the conditions under which they apply? lab multi-lora-fusion: Report a per-shape/per-workload cost constant fit from timing with its run-to-run spread AND its batch-to-batch spread, not a single-pass point estimate; a single pass here understated dispersion ~2x, and the batch-aggregate mean moved by more than its own sd. Ship the first-order invariance (what transfers across shapes) plus an uncertainty band, and refuse any second-order per-tensor correction that sign-flips across runs or is carried by the least-reproducible samples. Draft 2026-07-22T09:36:18Z 2461243.9002083 2026-07-22T09:36:19Z 2461243.9002199 research autopilot 20260722t090001z 3000 research-artifact-422c769c31ca157c 2026-07-22T09:36:18Z 2461243.9002083 S3ResearchAgent experiments/predict_working_set_knee.py (run_stability, --repeats) and committed receipt experiments/results/working_set_knee_cpu.json (experiment_id working_set_knee_predictor_v2_stability) benchmark partial_source research autopilot 20260722t090001z# 6786e6bdbe338234b49389be8eff77bc 3000 commit_2ebe798bd72f1668 2026-07-22T09:36:18Z 2461243.9002083 S3ResearchAgent GitHub mrcha033/multi-lora-fusion commit 2ebe798bd72f16689b44d373f90377b7b00a7ae2 code Commit emitted by this cycle; validation scope is recorded in the Lesson. partial_source research autopilot 20260722t090001z# b3bf8ab4c4899f3faa504ac34e351b29