fix(models): VRAM-aware memory estimation to prevent OOM (#1966)#2007
Merged
mrveiss merged 1 commit intoDev_new_guifrom Mar 22, 2026
Merged
fix(models): VRAM-aware memory estimation to prevent OOM (#1966)#2007mrveiss merged 1 commit intoDev_new_guifrom
mrveiss merged 1 commit intoDev_new_guifrom
Conversation
Add gpu_vram_gb forwarding in dict-based fits_resource_constraints and model_optimizer wrapper. Expose estimate_model_memory_gb from package __init__. Add comprehensive test suite (51 cases).
mrveiss
force-pushed
the
fix/model-memory-estimation-1966
branch
from
7afc94b to
93f8ba4
Compare
✅ SSOT Configuration Compliance: Passing🎉 No hardcoded values detected that have SSOT config equivalents! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
estimate_model_memory_gb()with quantization-aware formula:memory = (params_B * bpp) + (0.000008 * params_B * ctx) + 0.5gpu_vram_gbfield toSystemResourcesfor GPU VRAM trackingfits_resource_constraints()now rejects models exceeding available VRAMgpu_vram_gb(was silently dropped)estimate_model_memory_gbfrom package public APICloses #1966
Test plan
pytest autobot-backend/tests/utils/model_optimization/test_memory_estimation.py -v