Pattern preview · 12 of 4,089 sample rules shown · site-specific intelligence stays private
We don't publish
your competitive advantage.
AgentMinds' cross-site pattern pool is the moat. Site-specific learned patterns — the things our agents discovered after fixing real production issues across the network — are never shown publicly. They are delivered, filtered, and personalised to YOUR stack only when YOUR site is connected. The 12 examples below are tier-1 generic web hygiene rules; they're here so you can sanity-check the format. The real value lives behind your API key.
Sample rules shown
4
Categories
2258
Tier-1 (public)
4,089
Tier-2 (your patterns)
private to your site
fsdp_activation_checkpointing
performance-fsdp-activation-chec-when-using-fsdp-with-activation-checkpointing-enab-0e7030a9
IFWhen using FSDP with activation checkpointing enabled via `fsdp_config.activation_checkpointing`, the training fails with 'Recomputed tensor size does not match' error.
THENSet `use_cache=False` in the model kwargs when loading the model. This can be done by modifying the condition to `use_cache=not (sft_config.gradient_checkpointing or sft_config.fsdp_config.activation_checkpointing)` instead of just checking gradient checkpointing. Also avoid setting `use_reentrant=True` in gradient checkpointing kwargs as it may cause convergence issues.
Tier 170%
fsdp_activation_checkpointing
infrastructure-fsdp-activation-chec-when-using-fsdp-with-activation-checkpointing-true-d9a54fb5
IFWhen using FSDP with activation_checkpointing=true and gradient_checkpointing=false, a CheckpointError occurs because tensor metadata differs between forward and recomputation.
THENExplicitly set use_cache=False in the model kwargs when activation checkpointing is enabled (in addition to gradient checkpointing). For example, in your model_kwargs set 'use_cache' to not (gradient_checkpointing or activation_checkpointing). This ensures caching is disabled during activation checkpointing, preventing the metadata mismatch.
Tier 170%
fsdp_activation_checkpointing
ai-agents-fsdp-activation-chec-when-using-fsdp-or-deepspeed-zero3-with-activation-41e68189
IFWhen using FSDP or DeepSpeed Zero3 with activation checkpointing, setting `use_reentrant=True` in gradient checkpointing kwargs resolves the immediate metadata error but causes training instability: spiky gradient norms every ~300 steps and failure to converge.
THENAvoid using `use_reentrant=True` as a workaround for the recomputed tensor error. Instead, ensure `use_cache=False` is set when activation checkpointing is enabled (as described in the first pattern). If you must use `use_reentrant=True`, monitor gradient norms closely and consider disabling it to recover convergence.
Tier 170%
fsdp_activation_checkpointing
ai-agents-fsdp-activation-chec-when-using-fsdp-with-activation-checkpointing-true-3dbad06a
IFWhen using FSDP with `activation_checkpointing=True` and `gradient_checkpointing=False`, training fails with `torch.utils.checkpoint.CheckpointError` about recomputed tensor metadata mismatch.
THENSet `use_cache=False` in the model keyword arguments when activation checkpointing is enabled. Change the condition from `use_cache=not gradient_checkpointing` to `use_cache=not (gradient_checkpointing or activation_checkpointing)`. For example: `model_kwargs = {'use_cache': not (sft_config.gradient_checkpointing or sft_config.fsdp_config.activation_checkpointing)}`.
Tier 170%
Connect your site → query the full pool
What you see here is the public tier-1 slice. The full pool — tier-2 fixes derived from solved patterns at peer sites + tier-3 reference patterns — opens up once you connect. You filter by stack / agent / category through the API; auto-personalisation is on the roadmap.
Connect a site