continual_recovery_evaluator
Evaluate mechanism-faithful continual-learning recovery metrics and gate proxy evidence.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- continual_recovery_evaluator
- description
- Evaluate mechanism-faithful continual-learning recovery metrics and gate proxy evidence.
02 资源文件 2
03 SKILL.md 正文
Continual Recovery Evaluator
When To Use
Use this skill when reconstructing the episodic-memory lifelong language learning method from de Masson d'Autume et al. without relying on an original implementation repository.
Inputs
- Small text examples represented as dictionaries.
- Deterministic configuration values such as memory probability, replay interval, K, and adaptation steps.
Outputs
- Auditable Python objects or JSON-serializable dictionaries matching the module contract.
- Logs that expose mechanism execution rather than only final metrics.
Workflow
- Compute baseline and episodic retained accuracy on the same labels.
- Report gain over baseline as the proxy metric.
- Require explicit mechanism booleans before accepting proxy success.
Validation
Run python tests/test_continual_recovery_evaluator.py from this skill directory.
Limitations
The scripts are deterministic proxy utilities for bounded recovery. They do not train BERT or reproduce the full paper-scale datasets.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).