nn-and-state
Use Equinox neural-network layers, Sequential models, stateful layers, and inference mode.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- nn-and-state
- license
- Apache 2.0
- metadata
- { "disco-role": "operating" }
- description
- Use Equinox neural-network layers, Sequential models, stateful layers, and inference mode.
- disable-model-invocation
- true
02 资源文件 2
- 参考文档references/nn-and-state.md5.4 KB
- 参考文档references/troubleshooting.md3.5 KB
03 SKILL.md 正文
Neural Networks and State
Use this sub-skill for equinox.nn layers and stateful model workflows.
Use when
- The user asks how to build a model with
eqx.nn.Linear,MLP,Sequential,Conv*,MultiheadAttention,Embedding, pooling, RNN cells, or normalization layers. - A task needs
Dropout,BatchNorm,SpectralNorm,WeightNorm,inference_mode, or explicit PRNG key handling. - The user needs
eqx.nn.State,StateIndex,make_with_state,delete_init_state, or a custom stateful layer. - A model needs tied parameters with
eqx.nn.Shared. - A training loop combines Equinox layers with
filter_grad, Optax, andapply_updates.
Route elsewhere
- Use
../module-and-trees/for raweqx.Modulefield design, tree surgery, filtering, and optimizer parameter selection. - Use
../filtered-transformations/when the dominant issue is JIT, AD, vmap, pmap, callbacks, or sharding. - Use
../diagnostics-and-serialization/for saving/loading, runtime errors, debug tracing, or pretty printing. - Use
../internal-advanced/for semi-public internal loops and primitives.
Read first
references/nn-and-state.mdfor layer families, stateful workflows, single-example calling rules, and training-step patterns.references/troubleshooting.mdforBatchNorm, staleState, dropout,Sequential, and shared-weight failures.../../references/api-reference.mdfor cross-skill signatures.
Core workflow
- Choose the layer family and confirm whether it is stateless, stochastic, or stateful.
- Remember that most
equinox.nnlayers consume one example. Usejax.vmaporeqx.filter_vmaparound layer calls for batches. - Use
Sequentialfor ordered layers. Wrap activation functions witheqx.nn.Lambdawhen they live insideSequential. - Pass PRNG keys to constructors and to stochastic calls such as dropout.
- For stateful layers, construct with
eqx.nn.make_with_state(ModelClass)and thread the returnedStatethrough every call. - Toggle inference behavior with
eqx.nn.inference_mode(model, value=True). - Use
eqx.nn.Sharedfor intentional tied weights instead of relying on object identity in a PyTree. - For training, combine this sub-skill with
filtered-transformationsandmodule-and-trees.
Minimal validation
From the generated skill root (set EQUINOX_SKILL_ROOT to its absolute path),
run:
cd "$EQUINOX_SKILL_ROOT" && python scripts/smoke.py --mode nn
This validates tiny MLP, Sequential, custom state, and Shared examples.
It does not run expensive training or download datasets.
Scope note
This sub-skill distills Equinox's built-in layer, state, and sharing workflows into the bundled references and smoke helper. The source repository's tests, docs, and notebooks were construction evidence only, not runtime dependencies.
Key cautions
BatchNormmust run inside avmaporpmapwith a matchingaxis_namefor training statistics.State.setandState.updatereturn a new state and invalidate the old one.MLP(..., scan=True)changes the internal representation for compile-time reasons; do not call the scanned hidden layer stack directly.Sharedrequires matching source/destination structure, shapes, and dtypes.- Stochastic layers use explicit keys; do not hide key generation inside a JITed training step without a reproducible split plan.
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).