fix ddp/fsdp w gemma4 (#3584)
* fix ddp/fsdp w gemma4 * address pr comments * activation offloading fix and update agent docs for gemma4
This commit is contained in:
@@ -38,6 +38,8 @@ Agent-specific references:
|
||||
- [docs/agents/grpo.md](docs/agents/grpo.md) — GRPO online RL with reward functions
|
||||
- [docs/agents/reward_modelling.md](docs/agents/reward_modelling.md) — outcome and process reward models
|
||||
- [docs/agents/pretraining.md](docs/agents/pretraining.md) — continual pretraining
|
||||
- [docs/agents/model_architectures.md](docs/agents/model_architectures.md) — model-specific quirks (Gemma4, Qwen3.5 MoE, etc.)
|
||||
- [docs/agents/new_model_support.md](docs/agents/new_model_support.md) — debugging and adding support for new model architectures
|
||||
|
||||
## Config Pattern
|
||||
|
||||
|
||||
Reference in New Issue
Block a user