From a6dd28e8b47e01543c72a3d3b557c901a6f303df Mon Sep 17 00:00:00 2001
From: Pepijn <pepijn@huggingface.co>
Date: Thu, 16 Apr 2026 21:15:14 +0200
Subject: [PATCH] fix(profiling): tolerate groot dep-install failure

groot's only policy-specific dependency is flash-attn, which has no
prebuilt wheel for torch 2.10 and requires nvcc to build from source.
The CI image is based on nvidia/cuda:12.4.1-base, which ships the
CUDA runtime but not the compiler toolkit, so the source build fails
with `/usr/local/cuda/bin/nvcc: No such file or directory`. The
repo's own pyproject.toml already carries a TODO acknowledging this:
gr00t needs bespoke flash-attn install steps.

Treat this as an environmental limitation rather than a regression:
dep-install failures for groot are logged via `::warning::` and skip
the policy without failing the job. Dep-install failures for any
other policy remain fatal, so real regressions still surface.

Made-with: Cursor
---
 .github/workflows/model_profiling.yml | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/model_profiling.yml b/.github/workflows/model_profiling.yml
index 284879e3d..80a6746d0 100644
--- a/.github/workflows/model_profiling.yml
+++ b/.github/workflows/model_profiling.yml
@@ -161,6 +161,18 @@ jobs:
                 esac
               }
 
+              # Policies whose dep-install may fail due to environment constraints
+              # (e.g. groot requires compiling flash-attn, which needs nvcc; the CI
+              # image only ships the CUDA runtime). Install failures for these are
+              # logged as warnings and do not fail the job. See the TODO next to
+              # `lerobot[groot]` in pyproject.toml.
+              is_install_failure_tolerated() {
+                case "$1" in
+                  groot) return 0 ;;
+                  *) return 1 ;;
+                esac
+              }
+
               overall_status=0
               for raw_policy in "${policies_to_run[@]}"; do
                 policy="$(echo "${raw_policy}" | xargs)"
@@ -183,8 +195,12 @@ jobs:
                 # build isolation for flash-attn specifically.
                 sync_cmd+=(--no-build-isolation-package flash-attn)
                 if ! "${sync_cmd[@]}"; then
-                  echo "Dependency install failed for ${policy}; skipping." >&2
-                  overall_status=1
+                  if is_install_failure_tolerated "${policy}"; then
+                    echo "::warning::Dependency install failed for ${policy} (known-fragile); skipping."
+                  else
+                    echo "Dependency install failed for ${policy}; skipping." >&2
+                    overall_status=1
+                  fi
                   echo "::endgroup::"
                   continue
                 fi