Move LeRobot pin to 0.6.1 + draccus 0.11.6 (drops GPL pyyaml-include)

README.md

@@ -282,7 +282,7 @@ Advanced/SO-100/internal commands stay callable directly (`config`, `calibrate`,
 
 ### Install notes
 
-- `[monolithic]` extra is required for the cos=+1.000000 verified export path (pins transformers==5.3.0)
+- `[monolithic]` extra is required for the cos=+1.000000 verified export path (pins transformers==5.5.4, the release LeRobot 0.6.1 supports)
 - CPU-only: `pip install 'fastcrest-tether[serve,onnx,monolithic]'`
 - GPU install needs the FULL cuDNN 9 system library (not just the pip wheel). Easiest path: NVIDIA's container `docker run --gpus all -it nvcr.io/nvidia/tensorrt:24.10-py3`, then `apt-get install -y clang` (for lerobot→evdev), then the pip install
 - `tether serve` errors loudly if cuDNN can't load — no silent CPU fallback

pyproject.toml

@@ -29,7 +29,7 @@ dependencies = [
     # compiled against numpy 1.x ABI; numpy 2.x's ABI break corrupts ORT +
     # JAX wheels on aarch64. On x86_64 (Modal A100, customer desktops) +
     # arm64 (M-series Mac dev hosts) numpy 2.x is fine, AND the
-    # [monolithic] extra's lerobot==0.5.1 dep REQUIRES numpy>=2.0 — pinning
+    # [monolithic] extra's lerobot==0.6.1 dep REQUIRES numpy>=2.0 — pinning
     # numpy<2 globally makes lerobot uninstallable on Modal (caught by the
     # 2026-05-20 lift #4 smoke fire). Split via PEP-508 platform marker.
     "numpy>=1.24.0,<2.0; platform_machine == 'aarch64'",
@@ -39,12 +39,11 @@ dependencies = [
     # loading for the auto-detect path. Apr-14 install-path verification caught
     # that omitting these breaks `tether export` even with [serve,gpu].
     "huggingface_hub>=0.20.0",
-    # Base allows 4.40 → 5.3.x. [monolithic] extra pins ==5.3.0 exactly (5.4+ has
-    # a q_length regression that breaks onnx-diagnostic patches). Without the
-    # upper bound, pip would pull 5.4/5.5 here and conflict with [monolithic].
-    # Without raising the upper bound past 5.0, [monolithic] can't install
-    # alongside the base (the v0.2.1 customer-dogfood finding).
-    "transformers>=4.40,<5.4",
+    # Base allows 4.40 → 5.5.x. [monolithic] pins ==5.5.4 exactly, inside
+    # LeRobot 0.6.1's declared >=5.4,<5.6 (on 5.3 its pi0/pi0.5 embeddings are
+    # mis-scaled; Studio ADR 0003 correction 2026-10-12). The upper bound keeps
+    # pip from pulling an unqualified 5.6+ here.
+    "transformers>=4.40,<5.6",
     "onnx>=1.15.0",
     "onnxscript>=0.1.0",
     # TetherClient (Phase 0.5 customer-sdk) — sync + async HTTP client.
@@ -141,32 +140,42 @@ comply = []
 # gate in GOALS.yaml. Heavy (pulls torch, torchvision, accelerate, etc.) —
 # that's why it's a separate extra, not a base dep.
 #
-# lerobot 0.5.x requires Python >=3.12. Jetson (JetPack 6) ships 3.10,
+# lerobot 0.6.x requires Python >=3.12. Jetson (JetPack 6) ships 3.10,
 # so we gate lerobot behind a version marker — pip skips it on 3.10/3.11
 # instead of hard-failing with ResolutionImpossible. Native parity
 # verification should be run on a Python 3.12+ host.
 native = [
-    "lerobot==0.5.1; python_version >= '3.12'",
+    "transformers==5.5.4",
+    "lerobot==0.6.1; python_version >= '3.12'",
+    "draccus==0.11.6; python_version >= '3.12'",
     "num2words",
+    "accelerate>=1.14,<2",
+    "diffusers==0.39.0",
 ]
 # Monolithic ONNX export — cos=1.0 verified production path. Runs locally
 # via `tether export --monolithic` (the DEFAULT as of v0.2.1). Requires
-# transformers==5.3.0 EXACTLY (5.4+ has a q_length regression in
-# masking_utils.sdpa_mask that breaks onnx-diagnostic patches). Base pin
-# `transformers>=4.40,<5.4` permits this extra to pin-to-exact.
+# transformers==5.5.4 EXACTLY: LeRobot 0.6.1 needs >=5.4,<5.6, and the
+# exporter is qualified on this release (tests/_lerobot_pi_golden.py runs the
+# full onnx-diagnostic export against the pre-migration golden).
 #
-# lerobot 0.5.x requires Python >=3.12. On Jetson (Python 3.10) the
+# lerobot 0.6.x requires Python >=3.12. On Jetson (Python 3.10) the
 # monolithic export can't run locally — export on a cloud/desktop host
 # (Python 3.12+) and `tether serve` the resulting ONNX on the Jetson
 # with `pip install 'fastcrest-tether[serve]'` only.
 monolithic = [
-    "lerobot==0.5.1; python_version >= '3.12'",
-    "transformers==5.3.0",
+    "lerobot==0.6.1; python_version >= '3.12'",
+    "draccus==0.11.6; python_version >= '3.12'",
+    "transformers==5.5.4",
+    # onnx-diagnostic's export patches reference a torch 2.8+ symbol;
+    # _require_monolithic_deps refuses older torch with the same floor.
+    "torch>=2.8",
     "onnx-diagnostic>=0.9",
     "onnxscript>=0.1",
     "optree",
     "scipy",
     "num2words",
+    "accelerate>=1.14,<2",
+    "diffusers==0.39.0",
 ]
 # Task-success evaluation (heavy sim deps). Gated behind this extra so the
 # base install stays light. Use with `tether bench --benchmark libero_10`.
@@ -177,8 +186,14 @@ eval = [
     "gymnasium",
     "h5py",
 ]
+# Spell out the SmolVLA dependencies (LeRobot's transformers-dep extra,
+# >=5.4,<5.6) at the exact qualified transformers.
 eval-local = [
-    "lerobot[smolvla]==0.5.1; python_version >= '3.12' and sys_platform == 'linux'",
+    "transformers==5.5.4; python_version >= '3.12' and sys_platform == 'linux'",
+    "num2words>=0.5.14,<0.6; python_version >= '3.12' and sys_platform == 'linux'",
+    "accelerate>=1.14,<2; python_version >= '3.12' and sys_platform == 'linux'",
+    "lerobot==0.6.1; python_version >= '3.12' and sys_platform == 'linux'",
+    "draccus==0.11.6; python_version >= '3.12' and sys_platform == 'linux'",
     "peft; python_version >= '3.12' and sys_platform == 'linux'",
     "mujoco==3.3.2; sys_platform == 'linux'",
     "robosuite==1.4.1; sys_platform == 'linux'",
@@ -212,13 +227,14 @@ tracing = [
 #   pip install 'fastcrest-tether[lerobot]'
 #   tether serve bundle/ --embodiment so_arm100 --port /dev/ttyUSB0
 #
-# lerobot 0.5.x requires Python >=3.12 (we skip on 3.10/3.11 to avoid pip's
+# lerobot 0.6.x requires Python >=3.12 (we skip on 3.10/3.11 to avoid pip's
 # ResolutionImpossible; users on JetPack 6 Python 3.10 can still construct an
 # adapter + run the conversion math, they just can't open a serial bus until
 # they upgrade to Python 3.12 or install scservo_sdk directly via the [so100]
 # extra).
 lerobot = [
-    "lerobot>=0.5.1; python_version >= '3.12'",
+    "lerobot==0.6.1; python_version >= '3.12'",
+    "draccus==0.11.6; python_version >= '3.12'",
 ]
 # SO-100 hardware extra — installs the scservo_sdk Python package on the
 # Raspberry Pi / host wired to the arm. Separate from [lerobot] because the
@@ -234,9 +250,10 @@ so100 = [
 # RTC-enabled deployments. Skeleton + config validation work without this
 # extra; only the actual processor construction needs it.
 #
-# lerobot 0.5.x requires Python >=3.12 (skipped on 3.10/3.11).
+# lerobot 0.6.x requires Python >=3.12 (skipped on 3.10/3.11).
 rtc = [
-    "lerobot==0.5.1; python_version >= '3.12'",
+    "lerobot==0.6.1; python_version >= '3.12'",
+    "draccus==0.11.6; python_version >= '3.12'",
 ]
 # Curate format-converter extras. Phase 1 ships LeRobot v3 + HDF5 with the
 # core install (parquet via pyarrow which huggingface_hub already pulls; h5py
@@ -270,7 +287,7 @@ curate-rlds = [
 
 # Jetson / ARM64 edge stack.
 #   - Skips [gpu] x86_64 wheels (onnxruntime-gpu PyPI has no aarch64 builds)
-#   - Skips lerobot (0.5.1 requires Python 3.12; JetPack 6 ships 3.10)
+#   - Skips lerobot (0.6.1 requires Python 3.12; JetPack 6 ships 3.10)
 #   - User must pre-install Jetson Zoo onnxruntime-gpu from pypi.jetson-ai-lab.io
 #     and mount host CUDA via --runtime=nvidia.
 jetson = [
@@ -281,7 +298,7 @@ jetson = [
     "jsonschema>=4.0",
     "prometheus-client>=0.19.0",
     # monolithic export stack minus lerobot
-    "transformers==5.3.0",
+    "transformers==5.5.4",
     "onnx-diagnostic>=0.9",
     "onnxscript>=0.1",
     "optree",

scripts/local_pi05_monolithic_parity.py

@@ -34,36 +34,6 @@
     sys.modules[_mod] = _stub
 
 
-def _patch_pi05_for_transformers() -> None:
-    from lerobot.policies.pi05 import modeling_pi05
-    from lerobot.policies import pi_gemma
-    from transformers import masking_utils
-
-    def patched_embed_image(self, image):
-        out_dtype = image.dtype
-        if image.dtype != torch.float32:
-            image = image.to(torch.float32)
-        output = self.paligemma.model.get_image_features(image)
-        features = output.pooler_output if hasattr(output, "pooler_output") else output
-        features = features * self.paligemma.config.text_config.hidden_size**0.5
-        if features.dtype != out_dtype:
-            features = features.to(out_dtype)
-        return features
-
-    modeling_pi05.PaliGemmaWithExpertModel.embed_image = patched_embed_image
-
-    original = masking_utils.create_causal_mask
-
-    def causal_mask_shim(*args, **kwargs):
-        if "inputs_embeds" in kwargs and "input_embeds" not in kwargs:
-            kwargs["input_embeds"] = kwargs.pop("inputs_embeds")
-        return original(*args, **kwargs)
-
-    masking_utils.create_causal_mask = causal_mask_shim
-    if hasattr(pi_gemma, "create_causal_mask"):
-        pi_gemma.create_causal_mask = causal_mask_shim
-
-
 def _repo_commit() -> str:
     root = Path(__file__).resolve().parents[1]
     try:
@@ -160,7 +130,8 @@ def main(argv: list[str] | None = None) -> int:
     if args.num_steps <= 0:
         raise ValueError("--num-steps must be positive.")
 
-    _patch_pi05_for_transformers()
+    # Reference is native LeRobot 0.6.1 under the qualified transformers
+    # (5.5.4): no embedding or mask shims (Studio ADR 0003 correction 2026-10-12).
 
     import onnxruntime as ort
     from huggingface_hub import snapshot_download

scripts/local_pi0_monolithic_parity.py

@@ -35,44 +35,6 @@
     sys.modules[_mod] = _stub
 
 
-def _patch_pi0_for_transformers_457() -> None:
-    from lerobot.policies.pi0 import modeling_pi0
-
-    def patched_embed_image(self, image):
-        out_dtype = image.dtype
-        if image.dtype != torch.float32:
-            image = image.to(torch.float32)
-        image_outputs = self.paligemma.model.get_image_features(image)
-        features = (
-            image_outputs.pooler_output
-            if hasattr(image_outputs, "pooler_output")
-            else image_outputs
-        )
-        features = features * self.paligemma.config.text_config.hidden_size**0.5
-        if features.dtype != out_dtype:
-            features = features.to(out_dtype)
-        return features
-
-    modeling_pi0.PaliGemmaWithExpertModel.embed_image = patched_embed_image
-
-
-def _patch_create_causal_mask_kwarg() -> None:
-    from transformers import masking_utils
-
-    original = masking_utils.create_causal_mask
-
-    def shim(*args, **kwargs):
-        if "inputs_embeds" in kwargs and "input_embeds" not in kwargs:
-            kwargs["input_embeds"] = kwargs.pop("inputs_embeds")
-        return original(*args, **kwargs)
-
-    masking_utils.create_causal_mask = shim
-    from lerobot.policies import pi_gemma
-
-    if hasattr(pi_gemma, "create_causal_mask"):
-        pi_gemma.create_causal_mask = shim
-
-
 def _repo_commit() -> str:
     root = Path(__file__).resolve().parents[1]
     try:
@@ -167,8 +129,8 @@ def main(argv: list[str] | None = None) -> int:
     if args.num_steps <= 0:
         raise ValueError("--num-steps must be positive.")
 
-    _patch_pi0_for_transformers_457()
-    _patch_create_causal_mask_kwarg()
+    # Reference is native LeRobot 0.6.1 under the qualified transformers
+    # (5.5.4): no embedding or mask shims (Studio ADR 0003 correction 2026-10-12).
 
     import onnxruntime as ort
     from huggingface_hub import snapshot_download

scripts/modal_gr00t_lerobot_probe.py

@@ -1,6 +1,6 @@
-"""Quick probe — what does lerobot 0.5.1 actually expose for GR00T?
+"""Quick probe — what does lerobot 0.6.1 actually expose for GR00T?
 
-lerobot-0.5.1 on Modal may or may not have GR00T support. The cloned
+lerobot-0.6.1 on Modal may or may not have GR00T support. The cloned
 local lerobot is `main` (newer). Need to reconcile.
 
 Prints the actual module contents of lerobot's groot subpackage.
@@ -23,7 +23,7 @@
         "numpy",
         "safetensors>=0.4.0",
         "huggingface_hub",
-        "lerobot==0.5.1",
+        "lerobot==0.6.1",
         "num2words",
     )
 )
@@ -52,7 +52,7 @@ def probe():
 
     # Attempt to import groot_n1 + list symbols
     try:
-        from lerobot.policies.groot import groot_n1
+        from lerobot.policies.groot import groot_n1_7 as groot_n1
         print(f"\ngroot_n1 symbols (top-level, non-dunder):")
         for name in sorted(dir(groot_n1)):
             if not name.startswith("_"):
@@ -64,7 +64,7 @@ def probe():
 
     # Attempt action_head
     try:
-        from lerobot.policies.groot.action_head import flow_matching_action_head as fma
+        from lerobot.policies.groot.action_head import cross_attention_dit as fma
         print(f"\nflow_matching_action_head symbols:")
         for name in sorted(dir(fma)):
             if not name.startswith("_"):

scripts/modal_groot_export_parity_pinned.py

@@ -46,7 +46,7 @@
 )
 
 HF_CACHE_PATH = "/root/.cache/huggingface"
-PARITY_OUT_PATH = "/parity_out"
+PARITY_OUT_PATH = "/parity_out/lerobot-061-20261011"
 
 
 def _hf_secret():
@@ -63,24 +63,26 @@ def _hf_secret():
     modal.Image.debian_slim(python_version="3.12")
     .apt_install("git")
     .pip_install(
-        "torch",
+        # torch>=2.8: onnx-diagnostic 0.9.x torch_export_patches needs it (see pi0 vehicle).
+        "torch>=2.8,<2.12",
         "safetensors>=0.4.0",
         "huggingface_hub",
-        # transformers==5.3.0 EXACTLY: the monolithic exporter refuses
+        # transformers==5.5.4 EXACTLY: the monolithic exporter refuses
         # anything else.
-        "transformers==5.3.0",
+        "transformers==5.5.4",
         "onnx>=1.16",
         "onnxruntime>=1.20",
         "onnxscript>=0.1",
         # monolithic dep group (export_gr00t_monolithic gates on these):
-        "lerobot==0.5.1",
+        "lerobot==0.6.1",
         "num2words",
+        "diffusers==0.39.0",
         "onnx-diagnostic>=0.9",
         "optree",
         "scipy",
         "accelerate",
-        "draccus",
-        "numpy",
+        "draccus==0.11.6",
+        "numpy==2.2.6",
         "Pillow",
         "typer",
         "rich",
@@ -122,15 +124,15 @@ def _hf_secret():
     timeout=3600,
     volumes={
         HF_CACHE_PATH: _hf_cache_volume,
-        PARITY_OUT_PATH: _parity_out_volume,
+        "/parity_out": _parity_out_volume,
     },
     secrets=[_hf_secret()],
 )
 def run_export_parity(
     model_revision: str = GROOT_REVISION,
     tether_revision: str = TETHER_REVISION,
     embodiment_id: int = 0,
-    reuse_export: bool = True,
+    reuse_export: bool = False,
     watchdog_seconds: float = 3300,
 ) -> dict:
     import subprocess
@@ -322,8 +324,13 @@ def _progress(stage: str) -> None:
 
 
 @app.local_entrypoint()
-def main() -> None:
-    result = run_export_parity.remote()
+def main(
+    tether_revision: str = TETHER_REVISION,
+    watchdog_seconds: float = 1800,
+) -> None:
+    result = run_export_parity.remote(
+        tether_revision=tether_revision, watchdog_seconds=watchdog_seconds
+    )
     print("\n=== RESULT ===")
     for key, value in result.items():
         print(f"  {key}: {value}")

scripts/modal_layer_pruning_profile.py

@@ -65,8 +65,8 @@ def _build_bust() -> str:
     modal.Image.debian_slim(python_version="3.12")
     .apt_install("git")
     .pip_install(
-        "lerobot==0.5.1",
-        "transformers==5.3.0",
+        "lerobot==0.6.1",
+        "transformers==5.5.4",
         "num2words",
         "safetensors>=0.4.0",
         "scipy",
@@ -164,6 +164,7 @@ def hook(_module, _inp, output):
                 images = [img, img, img]
                 img_masks = [mask, mask, mask]
                 from lerobot.policies.pi05.modeling_pi05 import make_att_2d_masks
+                from lerobot.policies.common.vla_utils import prepare_attention_masks_4d
                 prefix_embs, prefix_pad_masks, prefix_att_masks = (
                     policy.model.embed_prefix(
                         images, img_masks, lang_tokens, lang_masks,
@@ -172,7 +173,7 @@ def hook(_module, _inp, output):
                 prefix_att_2d = make_att_2d_masks(prefix_pad_masks, prefix_att_masks)
                 prefix_position_ids = torch.cumsum(prefix_pad_masks, dim=1) - 1
                 prefix_att_2d_4d = (
-                    policy.model._prepare_attention_masks_4d(prefix_att_2d)
+                    prepare_attention_masks_4d(prefix_att_2d)
                 )
                 language_model.config._attn_implementation = "eager"
                 _ = policy.model.paligemma_with_expert.forward(