Deprecate ram/vram configs for smoother migration path to dynamic…

… limits (#7526)

## Summary

Changes:
- Deprecate `ram` and `vram` configs. If these are set in invokeai.yaml,
they will be ignored.
- Create new `max_cache_ram_gb` and `max_cache_vram_gb` configs with the
same definitions as the old configs.

The main motivation of this change is to make the migration path
smoother for users who had previously added `ram` /`vram` to their
config files. Now, these users will be automatically migrated into the
new dynamic limit behavior (which is better in most cases). These users
will have to manually re-add `max_cache_ram_gb` and `max_cache_vram_gb`
to their configs if they wish to go back to specifying manual limits.

## Related Issues / Discussions

See the release notes for RC v5.6.0rc1 for the old migration behavior
that we are trying to improve:
https://github.com/invoke-ai/InvokeAI/releases/tag/v5.6.0rc1

## QA Instructions

- [x] Test that if `ram` or `vram` are present in a user's
`invokeai.yaml`, these values are ignored.
- [x] Test that `max_cache_ram_gb` and `max_cache_vram_gb` are applied,
if set.

## Merge Plan

- Don't forget to update the RC release notes accordingly.

## Checklist

- [x] _The PR has a short but descriptive title, suitable for a
changelog_
- [x] _Tests added / updated (if applicable)_
- [x] _Documentation added / updated (if applicable)_
- [ ] _Updated `What's New` copy (if doing a release after this PR)_

invokeai/app/services/config/config_default.py

@@ -82,12 +82,14 @@ class InvokeAIAppConfig(BaseSettings):
         profile_graphs: Enable graph profiling using `cProfile`.
         profile_prefix: An optional prefix for profile output files.
         profiles_dir: Path to profiles output directory.
-        ram: The maximum amount of CPU RAM to use for model caching in GB. If unset, the limit will be configured based on the available RAM. In most cases, it is recommended to leave this unset.
-        vram: The amount of VRAM to use for model caching in GB. If unset, the limit will be configured based on the available VRAM and the device_working_mem_gb. In most cases, it is recommended to leave this unset.
-        lazy_offload: DEPRECATED: This setting is no longer used. Lazy-offloading is enabled by default. This config setting will be removed once the new model cache behaviour is out of beta.
+        max_cache_ram_gb: The maximum amount of CPU RAM to use for model caching in GB. If unset, the limit will be configured based on the available RAM. In most cases, it is recommended to leave this unset.
+        max_cache_vram_gb: The amount of VRAM to use for model caching in GB. If unset, the limit will be configured based on the available VRAM and the device_working_mem_gb. In most cases, it is recommended to leave this unset.
         log_memory_usage: If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.
         device_working_mem_gb: The amount of working memory to keep available on the compute device (in GB). Has no effect if running on CPU. If you are experiencing OOM errors, try increasing this value.
         enable_partial_loading: Enable partial loading of models. This enables models to run with reduced VRAM requirements (at the cost of slower speed) by streaming the model from RAM to VRAM as its used. In some edge cases, partial loading can cause models to run more slowly if they were previously being fully loaded into VRAM.
+        ram: DEPRECATED: This setting is no longer used. It has been replaced by `max_cache_ram_gb`, but most users will not need to use this config since automatic cache size limits should work well in most cases. This config setting will be removed once the new model cache behavior is stable.
+        vram: DEPRECATED: This setting is no longer used. It has been replaced by `max_cache_vram_gb`, but most users will not need to use this config since automatic cache size limits should work well in most cases. This config setting will be removed once the new model cache behavior is stable.
+        lazy_offload: DEPRECATED: This setting is no longer used. Lazy-offloading is enabled by default. This config setting will be removed once the new model cache behavior is stable.
         device: Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.<br>Valid values: `auto`, `cpu`, `cuda`, `cuda:1`, `mps`
         precision: Floating point precision. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system.<br>Valid values: `auto`, `float16`, `bfloat16`, `float32`
         sequential_guidance: Whether to calculate guidance in serial instead of in parallel, lowering memory requirements.
@@ -155,12 +157,15 @@ class InvokeAIAppConfig(BaseSettings):
     profiles_dir:                  Path = Field(default=Path("profiles"),   description="Path to profiles output directory.")
 
     # CACHE
-    ram:                Optional[float] = Field(default=None, gt=0,         description="The maximum amount of CPU RAM to use for model caching in GB. If unset, the limit will be configured based on the available RAM. In most cases, it is recommended to leave this unset.")
-    vram:               Optional[float] = Field(default=None, ge=0,         description="The amount of VRAM to use for model caching in GB. If unset, the limit will be configured based on the available VRAM and the device_working_mem_gb. In most cases, it is recommended to leave this unset.")
-    lazy_offload:                  bool = Field(default=True,               description="DEPRECATED: This setting is no longer used. Lazy-offloading is enabled by default. This config setting will be removed once the new model cache behaviour is out of beta.")
+    max_cache_ram_gb:   Optional[float] = Field(default=None, gt=0,         description="The maximum amount of CPU RAM to use for model caching in GB. If unset, the limit will be configured based on the available RAM. In most cases, it is recommended to leave this unset.")
+    max_cache_vram_gb:  Optional[float] = Field(default=None, ge=0,         description="The amount of VRAM to use for model caching in GB. If unset, the limit will be configured based on the available VRAM and the device_working_mem_gb. In most cases, it is recommended to leave this unset.")
     log_memory_usage:              bool = Field(default=False,              description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.")
     device_working_mem_gb:        float = Field(default=3,                  description="The amount of working memory to keep available on the compute device (in GB). Has no effect if running on CPU. If you are experiencing OOM errors, try increasing this value.")
     enable_partial_loading:        bool = Field(default=False,              description="Enable partial loading of models. This enables models to run with reduced VRAM requirements (at the cost of slower speed) by streaming the model from RAM to VRAM as its used. In some edge cases, partial loading can cause models to run more slowly if they were previously being fully loaded into VRAM.")
+    # Deprecated CACHE configs
+    ram:                Optional[float] = Field(default=None, gt=0,         description="DEPRECATED: This setting is no longer used. It has been replaced by `max_cache_ram_gb`, but most users will not need to use this config since automatic cache size limits should work well in most cases. This config setting will be removed once the new model cache behavior is stable.")
+    vram:               Optional[float] = Field(default=None, ge=0,         description="DEPRECATED: This setting is no longer used. It has been replaced by `max_cache_vram_gb`, but most users will not need to use this config since automatic cache size limits should work well in most cases. This config setting will be removed once the new model cache behavior is stable.")
+    lazy_offload:                  bool = Field(default=True,               description="DEPRECATED: This setting is no longer used. Lazy-offloading is enabled by default. This config setting will be removed once the new model cache behavior is stable.")
 
     # DEVICE
     device:                      DEVICE = Field(default="auto",             description="Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.")

invokeai/app/services/model_manager/model_manager_default.py

@@ -84,8 +84,8 @@ def build_model_manager(
         ram_cache = ModelCache(
             execution_device_working_mem_gb=app_config.device_working_mem_gb,
             enable_partial_loading=app_config.enable_partial_loading,
-            max_ram_cache_size_gb=app_config.ram,
-            max_vram_cache_size_gb=app_config.vram,
+            max_ram_cache_size_gb=app_config.max_cache_ram_gb,
+            max_vram_cache_size_gb=app_config.max_cache_vram_gb,
             execution_device=execution_device or TorchDevice.choose_torch_device(),
             logger=logger,
         )

tests/backend/model_manager/model_manager_fixtures.py

@@ -94,8 +94,8 @@ def mm2_loader(mm2_app_config: InvokeAIAppConfig) -> ModelLoadServiceBase:
     ram_cache = ModelCache(
         execution_device_working_mem_gb=mm2_app_config.device_working_mem_gb,
         enable_partial_loading=mm2_app_config.enable_partial_loading,
-        max_ram_cache_size_gb=mm2_app_config.ram,
-        max_vram_cache_size_gb=mm2_app_config.vram,
+        max_ram_cache_size_gb=mm2_app_config.max_cache_ram_gb,
+        max_vram_cache_size_gb=mm2_app_config.max_cache_vram_gb,
         execution_device=TorchDevice.choose_torch_device(),
         logger=InvokeAILogger.get_logger(),
     )