set var

.github/workflows/test_models.yml

@@ -3,9 +3,62 @@ on:
   pull_request:
     paths:
       - 'tinygrad_repo'
+      - 'openpilot/sunnypilot/modeld_v2/**'
   workflow_dispatch:
 
+env:
+  CI: 1
+  GIT_CONFIG_COUNT: 1
+  GIT_CONFIG_KEY_0: lfs.fetchexclude
+  GIT_CONFIG_VALUE_0: openpilot/selfdrive/modeld/models/big_driving_tinygrad.pkl
+
 jobs:
+  plain-artifact:
+    name: Plain artifact round trip and pickle converter
+    runs-on: ubuntu-24.04
+    env:
+      PYTHONPATH: ${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}
+      TINYGRAD_TESTS: 1
+    steps:
+      - uses: actions/checkout@v7
+      - run: ./tools/op.sh setup
+      - name: Build openpilot
+        run: scons -j$(nproc)
+      - name: Compile, load, cache and fuse a model with the pinned tinygrad
+        env:
+          DEV: CPU
+        run: tools/op.sh test -v openpilot/sunnypilot/modeld_v2/tests/test_plain_artifact.py
+      - name: Install LLVM 20 and ROCm comgr for the amd mock, as tinygrad_repo/.github/actions/setup-tinygrad does
+        run: |
+          . /etc/os-release
+          curl -fsSL https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
+          echo "deb http://apt.llvm.org/$VERSION_CODENAME/ llvm-toolchain-$VERSION_CODENAME-20 main" | sudo tee /etc/apt/sources.list.d/llvm.list
+          sudo mkdir -p /etc/apt/keyrings
+          curl -fsSL https://repo.radeon.com/rocm/rocm.gpg.key | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
+          echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/7.1 $VERSION_CODENAME main" | sudo tee /etc/apt/sources.list.d/rocm.list
+          printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600\n' | sudo tee /etc/apt/preferences.d/rocm-pin-600
+          sudo apt-get -qq update && sudo apt-get -qq install -y --no-install-recommends libllvm20 clang-20 lld-20 comgr
+          printf '/opt/rocm/lib\n/opt/rocm/lib64\n' | sudo tee /etc/ld.so.conf.d/rocm.conf && sudo ldconfig
+          echo "/usr/lib/llvm-20/bin" >> "$GITHUB_PATH"
+      - name: Convert a pickled USB+AMD jit and replay it under tinygrad's amd mock
+        env:
+          DEV: MOCKUSB+AMD
+          CHECK_OOB: 0
+          GMMU: 0
+        run: tools/op.sh test -v openpilot/sunnypilot/modeld_v2/tests/test_convert_upstream_pkl.py
+      - name: Where tinygrad moved, for the helper or failure point named above
+        if: failure() && github.event_name == 'pull_request'
+        run: |
+          git fetch -q --depth=1 origin "${{ github.base_ref }}"
+          old=$(git rev-parse "origin/${{ github.base_ref }}:tinygrad_repo") new=$(git rev-parse HEAD:tinygrad_repo)
+          git -C tinygrad_repo fetch -q origin "$old" || true
+          echo "tinygrad_repo $old -> $new, in what helpers.py and plain_artifact_compiler.py read:"
+          git -C tinygrad_repo diff "$old" "$new" -- tinygrad/uop/ops.py tinygrad/engine/jit.py tinygrad/engine/realize.py tinygrad/device.py \
+            tinygrad/helpers.py tinygrad/dtype.py tinygrad/renderer/__init__.py
+          echo "and in what convert_upstream_pkl.py decodes:"
+          git -C tinygrad_repo diff --stat "$old" "$new" -- tinygrad/runtime/autogen/am/pm4_nv.py tinygrad/runtime/autogen/amd_gpu.py
+          git -C tinygrad_repo diff "$old" "$new" -- tinygrad/runtime/support/hcq2.py tinygrad/runtime/support/usb.py tinygrad/runtime/ops_amd.py
+
   generate-matrix:
     runs-on: ubuntu-latest
     outputs:

openpilot/selfdrive/ui/sunnypilot/layouts/settings/models.py

@@ -243,9 +243,7 @@ class ModelsLayout(Widget):
     if ds.verifying in statuses:
       return {"name": name, "downloading": True, "progress": progress, "status_text": tr("verifying")}
     if ds.downloading in statuses:
-      speed = max((p.speed for p in progresses), default=0.0)
-      status_text = f"{speed / 1024 ** 2:.1f} MB/s" if speed > 0 else "--.- MB/s"
-      return {"name": name, "downloading": True, "progress": progress, "status_text": status_text}
+      return {"name": name, "downloading": True, "progress": progress}
     if statuses <= {ds.downloaded, ds.cached}:
       return {"name": name, "text_color": ON_COLOR, "icon": "icons/checkmark.png"}
     # circled_slash is authored grey; tinting it again only darkens it

openpilot/selfdrive/ui/sunnypilot/mici/layouts/models.py

@@ -257,7 +257,6 @@ class ModelsLayoutMici(NavScroller):
       count = 0
       verifying = False
       canceling = False
-      speed = 0.0
       for model in manager.selectedBundle.models:
         count += 1
         p = model.artifact.downloadProgress
@@ -266,7 +265,6 @@ class ModelsLayoutMici(NavScroller):
           progress += p.progress
           verifying = verifying or p.status == custom.ModelManagerSP.DownloadStatus.verifying
           canceling = canceling or p.canceling
-          speed = max(speed, p.speed)  # only one file downloads at a time, so the non-zero speed is the live one
         elif p.status in (custom.ModelManagerSP.DownloadStatus.downloaded,
                           custom.ModelManagerSP.DownloadStatus.cached):
           progress += 100.0
@@ -281,10 +279,7 @@ class ModelsLayoutMici(NavScroller):
       self.current_model_info.current_model_text.set_text(name_text)
       self.current_model_info.info_header.set_text(tr("progress") + self._download_progress)
       self.current_model_info.info_header._shimmer = True
-      progress_text = f"{progress/count:.2f}%"
-      if not verifying and not canceling:
-        progress_text += f"  |  {speed / 1024 ** 2:.1f} MB/s" if speed > 0 else "  |  --.- MB/s"
-      self.current_model_info.info_text.set_text(progress_text)
+      self.current_model_info.info_text.set_text(f"{progress/count:.2f}%")
 
     elif manager.selectedBundle and manager.selectedBundle.status == custom.ModelManagerSP.DownloadStatus.downloaded:
       self.current_model_info.info_header.set_text(tr("downloaded"))

openpilot/sunnypilot/modeld_v2/convert_upstream_pkl.py

@@ -7,6 +7,7 @@ See the LICENSE.md file in the root directory for more details.
 """
 import argparse
 import dataclasses
+import inspect
 import itertools
 import mmap
 import re
@@ -45,6 +46,11 @@ def _address(v):
   return _root(v.src[0]), add + start, size
 
 
+def _buffer(u):
+  from tinygrad.uop.ops import Ops
+  return u.buffer if u.op is Ops.BUFFER else getattr(u.arg, "buffer", None)
+
+
 def _patched(buf, topo) -> tuple[bytearray, dict]:
   from tinygrad.uop.ops import Ops
   blob, rows = bytearray(buf.max_numel() * buf.dtype.itemsize), {}
@@ -72,7 +78,7 @@ def _evaluate(u, env):
     table, index = _root(u.src[0].src[0]), _evaluate(u.src[0].src[1], env)
     return struct.unpack_from(u.dtype.fmt, table.arg, index * u.dtype.itemsize)[0] if table.op is Ops.BINARY and index is not None else None
   if u.op in GroupOp.ALU and None not in (values := [_evaluate(x, env) for x in u.src]):
-    return exec_alu(u.op, u.dtype, values, False)
+    return exec_alu(u.op, u.dtype, values, *([False] if "truncate_output" in inspect.signature(exec_alu).parameters else []))
   return None
 
 
@@ -112,7 +118,7 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
   from tinygrad.uop.ops import Ops
   submit = jit.captured._linear.src[0].without_after
   kernels, topo = submit.arg.aux.kernels, list(jit.captured._linear.toposort(enter_calls=True))
-  allocs = {str(u.tag): u for u in topo if u.op is Ops.ALLOC and u.tag is not None}
+  allocs = {str(name): u for u in topo if u.op is Ops.ALLOC and (name := getattr(u, "tag", None) or u.arg.name) is not None}
   (commands, patched), kernargs = _patched(allocs["cmdbuf_compute_0"], topo), allocs["kernargs_compute_0"]
   argument_words, pokes = _patched(kernargs, topo)[1], _input_pokes(submit, kernargs)
   sh = {name: getattr(amd_gpu, f"reg{name}") + amd_gpu.GC_BASE__INST0_SEG0 - pm4.PACKET3_SET_SH_REG_START
@@ -158,7 +164,7 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
         args.append({"input": pokes[slot][0]})
       elif slot in argument_words:
         base, at, nbytes = _address(argument_words[slot])
-        args.append({"buffer": buffers.setdefault(base, len(buffers)), "offset": at, "nbytes": nbytes or base.arg.buffer.nbytes, "dtype": u8})
+        args.append({"buffer": buffers.setdefault(base, len(buffers)), "offset": at, "nbytes": nbytes or base.max_numel() * base.dtype.itemsize, "dtype": u8})
     outs, ins = kernel[6]
     calls.append({"kind": "program", "name": re.sub(r"\x1b\[[0-9;]*m", "", kernel[1]), "lib": programs[image_alloc], "target": dataclasses.asdict(target),
                   "signature": [[f"data{i}", i, u8, [a.get("nbytes", 1)]] for i, a in enumerate(args)], "global_size": grid, "local_size": local,
@@ -166,12 +172,13 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
     needs_init |= {args[i]["buffer"] for i in ins if "buffer" in args[i] and args[i]["buffer"] not in written}
     written |= {args[i]["buffer"] for i in outs if "buffer" in args[i]}
 
+  assert all(_buffer(b) is not None for b, i in buffers.items() if i in needs_init), "a kernel reads a scratch before any kernel writes it"
   names = list(jit.captured.expected_names)
   inputs = [{"slot": slot, "name": names[slot] if slot < len(names) else None, "dtype": repr(u.dtype), "numel": int(u.max_numel()), "device": u.device}
             for slot, u in enumerate(_prepare_jit_inputs((), kwargs)[0])]
   header = {"input_names": names, "calls": calls, "returns": {"kind": "NoneType", "tensors": []}, "inputs": inputs,
-            "buffers": [{"nbytes": b.arg.buffer.nbytes, "device": b.arg.buffer.device, "dtype": u8}
-                        | ({"init": blob.add(b.arg.buffer.ensure_allocated().as_memoryview())} if i in needs_init else {}) for b, i in buffers.items()],
+            "buffers": [{"nbytes": bb.nbytes if (bb := _buffer(b)) else b.max_numel() * b.dtype.itemsize, "device": bb.device if bb else b.device, "dtype": u8}
+                        | ({"init": blob.add(bb.ensure_allocated().as_memoryview())} if i in needs_init else {}) for b, i in buffers.items()],
             "check": {"inputs": [[path, store(array), device] for path, array, device in frame["inputs"]],
                       "outputs": [store(array) for array in frame["outputs"]], "output_container": frame["output_container"]}}
   with sink:

openpilot/sunnypilot/modeld_v2/helpers.py

@@ -250,6 +250,12 @@ def _allocate_buffers(header: dict, blob: memoryview, device_map: dict | None, s
   return buffers
 
 
+def _fields(what, /, **values):  # a tinygrad dataclass built or replaced with the fields it has today: a dropped field is fine, a new required one is not
+  known = {field.name for field in dataclasses.fields(what)}
+  values = {name: value for name, value in values.items() if name in known}
+  return what(**values) if isinstance(what, type) else dataclasses.replace(what, **values)
+
+
 def _program_uop(call: dict, lib: bytes):
   from tinygrad.helpers import Target
   from tinygrad.uop.ops import KernelInfo, Ops, ProgramInfo, UOp
@@ -257,9 +263,9 @@ def _program_uop(call: dict, lib: bytes):
   for name, compact_slot, dtype, shape in call["signature"]:
     parameter = UOp.param(call["globals"][compact_slot], _dtype(dtype), math.prod(shape))
     image = (shape[0], shape[1]) if len(shape) == 3 and shape[2] == 4 else None
-    parameters.append(parameter.replace(arg=dataclasses.replace(parameter.arg, name=name, image=image)))
-  info = ProgramInfo(global_size=tuple(call["global_size"]), local_size=tuple(call["local_size"]), vars=(), globals=tuple(call["globals"]),
-                     outs=tuple(call["outs"]), ins=tuple(call["ins"]), target=Target(**call["target"]))
+    parameters.append(parameter.replace(arg=_fields(parameter.arg, name=name, image=image)))
+  info = _fields(ProgramInfo, global_size=tuple(call["global_size"]), local_size=tuple(call["local_size"]), globals=tuple(call["globals"]),
+                 outs=tuple(call["outs"]), ins=tuple(call["ins"]), target=_fields(Target, **call["target"]))
   return UOp(Ops.PROGRAM, src=(UOp(Ops.SINK, arg=KernelInfo(name=call["name"])), UOp(Ops.LINEAR, src=tuple(parameters)),
                                UOp(Ops.SOURCE, arg=""), UOp(Ops.BINARY, arg=lib)), arg=info)
 

openpilot/sunnypilot/modeld_v2/plain_artifact_compiler.py

@@ -23,7 +23,7 @@ def record_kernel_linear():
   recorded, hcq_compile, compile_linear = [], realize.hcq_compile, jit.compile_linear
 
   def recording_compile_linear(*args, **kwargs):
-    with mock.patch.object(realize, "hcq_compile", lambda linear, *a, **k: (recorded.append(linear), hcq_compile(linear, *a, **k))[1]):
+    with mock.patch.object(realize, "hcq_compile", lambda linear, *a, **k: (linear.src and recorded.append(linear), hcq_compile(linear, *a, **k))[1]):
       return compile_linear(*args, **kwargs)
 
   with mock.patch.object(jit, "compile_linear", recording_compile_linear):
@@ -38,6 +38,18 @@ def capture_frame(jit, kwargs: dict, output_container: str | None = None):
   return {"inputs": inputs, "outputs": [tensor.numpy().copy() for tensor in outputs], "output_container": output_container}, result
 
 
+def kernel_signature(ast, elf) -> list:
+  from tinygrad.dtype import AddrSpace
+  if hasattr(ast, "kernel_params"):
+    if any(p.arg.addrspace is AddrSpace.ALU for p in ast.kernel_params):
+      raise ValueError(f"{elf.name} takes a variable, which plain artifacts don't support")
+    compact = {slot: i for i, slot in enumerate(ast.arg.globals)}
+    return [[p.arg.name, compact[p.arg.slot], repr(p.dtype), [int(x) for x in p._shape]] for p in ast.kernel_params]
+  if not all(isinstance(slot, int) for _, slot, _, _ in elf.signature):
+    raise ValueError("TinyELF.signature lost its slots and this tinygrad has no UOp.kernel_params: update kernel_signature")
+  return [[name, slot, repr(dtype), [int(x) for x in shape]] for name, slot, dtype, shape in elf.signature]
+
+
 def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict, memoryview]:
   from tinygrad.uop.ops import Ops
   sink = tempfile.TemporaryFile(dir=".")
@@ -51,6 +63,12 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
     if uop.op is Ops.PARAM:
       input_specs.setdefault(uop.arg.slot, {"dtype": repr(uop.dtype), "numel": int(uop.max_numel()), "device": uop.device})
       return {"input": uop.arg.slot}
+    root, offset = uop, 0
+    while root.op in (Ops.AFTER, Ops.BITCAST, Ops.SHRINK):
+      offset, root = offset + (root.src[1].arg * root.src[0].dtype.itemsize if root.op is Ops.SHRINK else 0), root.src[0]
+    if root.op is Ops.ALLOC:
+      base = bases.setdefault(id(root), (len(bases), root, root.dtype))
+      return {"buffer": base[0], "offset": offset, "nbytes": int(uop.max_numel()) * uop.dtype.itemsize, "dtype": repr(uop.dtype)}
     buffer = uop.buffer
     root = buffer._base if buffer._base is not None else buffer
     base = bases.setdefault(id(root), (len(bases), root, uop.base.dtype if buffer._base is None else uop.dtype))
@@ -63,7 +81,7 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
       elf, info = ast.to_elf(), ast.arg
       global_size, local_size = info.launch_dims({})
       calls.append({"kind": "program", "name": elf.name, "lib": blob.add(bytes(elf.lib)), "target": dataclasses.asdict(elf.target),
-                    "signature": [[name, slot, repr(dtype), [int(x) for x in shape]] for name, slot, dtype, shape in elf.signature],
+                    "signature": kernel_signature(ast, elf),
                     "global_size": [int(x) for x in global_size], "local_size": [int(x) for x in local_size],
                     "globals": list(info.globals), "outs": list(info.outs), "ins": list(info.ins), "args": arguments})
       outs, ins = info.outs, info.ins
@@ -77,7 +95,9 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
 
   ret = jit.captured.ret
   returns = {"kind": type(ret).__name__, "tensors": [describe(t.uop.base) | {"shape": [int(x) for x in t.shape]} for t in flatten(ret)]}
-  buffers = [{"nbytes": base.nbytes, "device": base.device, "dtype": repr(dtype)}
+  from tinygrad.device import Buffer
+  assert not [base for index, base, _ in bases.values() if index in needs_init and not isinstance(base, Buffer)], "a kernel reads a scratch before writing it"
+  buffers = [{"nbytes": base.nbytes if isinstance(base, Buffer) else int(base.max_numel()) * dtype.itemsize, "device": base.device, "dtype": repr(dtype)}
              | ({"init": blob.add(base.as_memoryview())} if index in needs_init else {}) for index, base, dtype in bases.values()]
   names = list(jit.captured.expected_names)
   if check is not None:

openpilot/sunnypilot/modeld_v2/tests/test_convert_upstream_pkl.py

@@ -0,0 +1,121 @@
+"""
+Copyright (c) 2021-, Haibin Wen, sunnypilot, and a number of other contributors.
+
+This file is part of sunnypilot and is licensed under the MIT License.
+See the LICENSE.md file in the root directory for more details.
+"""
+import os
+import re
+import sys
+import tempfile
+import unittest
+from unittest import mock
+import numpy as np
+
+os.environ.setdefault("CHECK_OOB", "0")
+os.environ.setdefault("GMMU", "0")
+if sys.platform == "darwin" and os.environ.get("DEV", "").startswith("MOCKUSB"):  # the mock's VRAM is a memfd, which macOS lacks: an unlinked file is the same
+  from tinygrad.runtime.autogen import libc
+
+  def _memfd_create(name, flags):
+    fd, path = tempfile.mkstemp()
+    os.unlink(path)
+    return fd
+  libc.memfd_create = _memfd_create
+
+from openpilot.common.test import OpenpilotTestCase
+from openpilot.sunnypilot.modeld_v2 import convert_upstream_pkl
+from openpilot.sunnypilot.modeld_v2.convert_upstream_pkl import convert
+from openpilot.sunnypilot.modeld_v2.helpers import PlainJit, load_model
+from openpilot.sunnypilot.modeld_v2.plain_artifact_compiler import capture_frame
+
+IMG, DESIRE, STATE, OUT = (6, 8, 8), (8,), (4, 16), (1, 32)
+
+
+class TestConvertUpstreamPkl(OpenpilotTestCase):
+  @classmethod
+  def setUpClass(cls):
+    super().setUpClass()
+    if not os.environ.get("TINYGRAD_TESTS"):
+      raise unittest.SkipTest("TINYGRAD_TESTS not set. skipping converter test")
+    from tinygrad import Device, Tensor
+    assert Device.DEFAULT == "AMD" and getattr(Device["AMD"], "is_usb", False), f"{Device.DEFAULT} is not an AMD device behind the USB bridge"
+    assert (Tensor([1, 2, 3]) * 2).tolist() == [2, 4, 6]
+    cls.tmp = tempfile.TemporaryDirectory()
+    cls.rng = np.random.default_rng(0)
+    cls.weights = Tensor(cls.rng.standard_normal((16, 32)).astype(np.float32)).realize()
+    cls.bias = Tensor(cls.rng.standard_normal((1, 32)).astype(np.float32)).realize()
+    cls.input_specs = {"input_imgs": (IMG, "uint8", Device.DEFAULT), "desire": (DESIRE, "float32", Device.DEFAULT),
+                       "features": (STATE, "float32", Device.DEFAULT)}
+    cls.output_specs = {"outputs": (OUT, "float32", Device.DEFAULT), "next_features": (STATE, "float32", Device.DEFAULT)}
+
+  @classmethod
+  def tearDownClass(cls):
+    cls.tmp.cleanup()
+    super().tearDownClass()
+
+  def model(self, input_imgs, desire, features, output_buffers):
+    from tinygrad import Tensor
+    feat = features.mean(axis=0).reshape(1, 16) + input_imgs.float().mean() + desire.sum()
+    Tensor.realize(output_buffers["outputs"].assign((feat @ self.weights + self.bias).relu()),
+                   output_buffers["next_features"].assign(features[1:].cat(feat * 2)))
+
+  def inputs(self, seed: int) -> dict:
+    from examples.openpilot.helpers import allocate_inputs
+    rng = np.random.default_rng(seed)
+
+    def initialize(arrays: dict):
+      for value in arrays.values():
+        value[...] = rng.standard_normal(value.shape) if value.dtype.kind == "f" else rng.integers(0, 256, value.shape)
+    return allocate_inputs(self.input_specs, initialize) | {"output_buffers": allocate_inputs(self.output_specs)}
+
+  def jit(self):
+    from tinygrad import TinyJit
+    run = TinyJit(self.model, prune=True)
+    kwargs = self.inputs(1)
+    run(**kwargs)
+    run(**kwargs)
+    return run
+
+  def assert_matches_eager(self, plain, seed: int):
+    fresh, expected = self.inputs(seed), self.inputs(seed)
+    plain(**fresh)
+    self.model(**expected)
+    for name in self.output_specs:
+      assert np.array_equal(fresh["output_buffers"][name].numpy(), expected["output_buffers"][name].numpy()), name
+
+  def convert(self, jit) -> tuple[dict, memoryview]:
+    from tinygrad import Device
+    kwargs = self.inputs(2)
+    frame, _ = capture_frame(jit, kwargs, "output_buffers")
+    header, blob = convert(jit, kwargs, frame, Device[Device.DEFAULT].renderer.target)
+    kernels = jit.captured._linear.src[0].without_after.arg.aux.kernels
+    assert [call["name"] for call in header["calls"]] == [re.sub(r"\x1b\[[0-9;]*m", "", kernel[1]) for kernel in kernels]
+    assert all(re.fullmatch(r"\w+", call["name"]) for call in header["calls"]), "kernel names: failure point 1"
+    assert [(tuple(call["outs"]), tuple(call["ins"])) for call in header["calls"]] == [tuple(kernel[6]) for kernel in kernels], "outs/ins: failure point 1"
+    bound = {argument["input"] for call in header["calls"] for argument in call["args"] if "input" in argument}
+    assert bound == {spec["slot"] for spec in header["inputs"]}, f"input slots bound by pokes {sorted(bound)}: failure point 4"
+    assert [spec["name"] for spec in header["inputs"]][:len(self.input_specs)] == sorted(self.input_specs)
+    return header, blob
+
+  def test_converted_jit_matches_eager(self):  # the submit decoded into plain calls, replayed against its own frame
+    jit = self.jit()
+    plain = PlainJit(*self.convert(jit))
+    self.assert_matches_eager(plain, 3)
+    self.assert_matches_eager(plain, 4)
+
+  def test_pickle_round_trip_through_main(self):
+    from examples.openpilot.helpers import dump_pickle, load_pickle
+    from tinygrad.engine.realize import lower_and_compile
+    pkl, out = os.path.join(self.tmp.name, "tiny_tinygrad.pkl"), os.path.join(self.tmp.name, "tiny_plain.pkl")
+    dump_pickle({"run": self.jit(), "input_specs": self.input_specs, "output_specs": self.output_specs, "metadata": {"name": "tiny"}}, pkl)
+
+    artifact = load_pickle(pkl, out_of_band=True)
+    artifact["run"].captured._linear = lower_and_compile(artifact["run"].captured._linear)
+    self.assert_matches_eager(PlainJit(*self.convert(artifact["run"])), 5)
+
+    with mock.patch.object(sys, "argv", ["convert_upstream_pkl", pkl, out]):
+      convert_upstream_pkl.main()
+    bundle = load_model(out, cache=False, verify=True)
+    assert bundle["metadata"] == {"name": "tiny"} and bundle["input_specs"] == self.input_specs and bundle["output_specs"] == self.output_specs
+    self.assert_matches_eager(bundle["run"], 6)

openpilot/sunnypilot/modeld_v2/tests/test_plain_artifact.py

@@ -0,0 +1,162 @@
+"""
+Copyright (c) 2021-, Haibin Wen, sunnypilot, and a number of other contributors.
+
+This file is part of sunnypilot and is licensed under the MIT License.
+See the LICENSE.md file in the root directory for more details.
+"""
+import dataclasses
+import functools
+import inspect
+import os
+import sys
+import tempfile
+from unittest import mock
+import numpy as np
+import unittest
+
+import openpilot.sunnypilot.modeld_v2.helpers as helpers
+from openpilot.common.test import OpenpilotTestCase
+from openpilot.sunnypilot.modeld_v2 import compile_warp
+from openpilot.sunnypilot.modeld_v2.frame_fusion import frame_part, pack_layout
+from openpilot.sunnypilot.modeld_v2.helpers import PlainJit, cache_is_fresh, load_model, read_parts, write_bundle
+from openpilot.sunnypilot.modeld_v2.plain_artifact_compiler import capture_frame, record_kernel_linear, serialize_jit
+
+CAM_W, CAM_H, MODEL_W, MODEL_H = 32, 16, 16, 8
+FRAME = f"{CAM_W},{CAM_H},{CAM_W},{CAM_H},{CAM_H // 2},{CAM_W * CAM_H * 3 // 2}"
+FRAME_SIZE = CAM_W * CAM_H * 3 // 2
+HOST = {"desire": (8,), "traffic_convention": (2,)}
+STATE, OUT = (4, 16), (1, 32)
+
+
+def compile_jit(fn, inputs: dict, output_container: str | None = None) -> tuple[dict, memoryview]:
+  from tinygrad import TinyJit
+  run = TinyJit(fn, prune=True)
+  with record_kernel_linear() as recorded:
+    run(**inputs)
+    run(**inputs)
+    check, _ = capture_frame(run, inputs, output_container)
+  assert len(recorded) == 1, f"expected one captured kernel list, got {len(recorded)}"
+  return serialize_jit(run, recorded[0], check)
+
+
+class TestPlainArtifact(OpenpilotTestCase):
+  @classmethod
+  def setUpClass(cls):
+    super().setUpClass()
+    if not os.environ.get("TINYGRAD_TESTS"):
+      raise unittest.SkipTest("TINYGRAD_TESTS env var not set, skipping artifact test.")
+    from tinygrad import Tensor
+    cls.tmp = tempfile.TemporaryDirectory()
+    cls.rng = np.random.default_rng(0)
+    cls.weights = Tensor(cls.rng.standard_normal((16, 32)).astype(np.float32)).realize()
+    cls.bias = Tensor(cls.rng.standard_normal((1, 32)).astype(np.float32)).realize()
+
+  @classmethod
+  def tearDownClass(cls):
+    cls.tmp.cleanup()
+    super().tearDownClass()
+
+  def model(self, x, h):  # a two input, one weight model: the shape of a policy without the size
+    return ((x @ self.weights + self.bias).relu() + h.mean()).contiguous()
+
+  def tensors(self, seed: int):
+    from tinygrad import Tensor
+    rng = np.random.default_rng(seed)
+    return {"x": Tensor(rng.standard_normal((1, 16)).astype(np.float32)).realize(), "h": Tensor(rng.standard_normal((4, 16)).astype(np.float32)).realize()}
+
+  def artifact(self, name: str = "model") -> str:
+    path = os.path.join(self.tmp.name, f"{name}_tinygrad.pkl")
+    if not os.path.exists(path):
+      write_bundle(path, {"run": compile_jit(self.model, self.tensors(1))}, {"metadata": {"name": name}})
+    return path
+
+  def test_round_trip_matches_jit(self):  # compiler -> bundle -> PlainJit, replay verified, then fresh inputs bit exact with eager tinygrad
+    bundle = load_model(self.artifact(), cache=False, verify=True)
+    assert bundle["metadata"] == {"name": "model"} and isinstance(bundle["run"], PlainJit)
+    fresh = self.tensors(2)
+    assert np.array_equal(bundle["run"](**fresh).numpy(), self.model(**fresh).numpy())
+
+  def test_replay_check_catches_a_changed_kernel(self):
+    parts, extras = read_parts(self.artifact())
+    header, blob = parts["run"]
+    poisoned = dict(header, check=dict(header["check"], outputs=[header["check"]["inputs"][0][1]]))
+    with self.assertRaises(helpers.ArtifactMismatch):
+      PlainJit(poisoned, blob)
+
+  def test_cache_round_trip_holds_no_weights_and_is_rebuilt_when_stale(self):
+    path = self.artifact("cached")
+    expected = load_model(path, cache=False, verify=False)["run"](**self.tensors(3)).numpy()
+    load_model(path)
+    assert cache_is_fresh(path)
+    with open(f"{path}.cache", "rb") as file:
+      cache = file.read()
+    assert self.weights.numpy().tobytes() not in cache and len(cache) < os.path.getsize(path)
+    with mock.patch.object(helpers, "PlainJit", side_effect=AssertionError("a fresh cache must not rebuild")):
+      cached = load_model(path)
+    assert np.array_equal(cached["run"](**self.tensors(3)).numpy(), expected)
+    with mock.patch.object(helpers, "tinygrad_identity", return_value="another tinygrad"):
+      assert not cache_is_fresh(path)
+      assert isinstance(load_model(path)["run"], PlainJit)
+      assert cache_is_fresh(path)
+    assert not cache_is_fresh(path)  # keyed on the tinygrad that wrote it, so the next boot after a bump rebuilds once
+    os.utime(path)
+    with mock.patch.object(helpers, "tinygrad_identity", return_value="another tinygrad"):
+      assert not cache_is_fresh(path)
+
+  def test_fused_with_warp_matches_warp_then_model(self):
+    from tinygrad import Tensor
+    warp_path = os.path.join(self.tmp.name, "warp_tinygrad.pkl")
+    with mock.patch.object(sys, "argv", ["compile_warp", "--frame", FRAME, "--warp-to", f"{MODEL_W}x{MODEL_H}", "--output", warp_path]):
+      compile_warp.main()
+    warp = load_model(warp_path, cache=False)["run"]
+
+    def native(new_img, desire, traffic_convention, state_feat_q, output_buffers):
+      feat = state_feat_q.mean(axis=0).reshape(1, 16) + new_img.float().mean() + desire.sum() + traffic_convention[0]
+      Tensor.realize(output_buffers["outputs"].assign((feat @ self.weights + self.bias).relu()),
+                     output_buffers["next_state_feat_q"].assign(state_feat_q[1:].cat(feat * 2)))
+
+    def model_inputs(new_img):
+      return {"new_img": new_img} | {name: Tensor(np.ones(shape, np.float32) * 0.5).realize() for name, shape in HOST.items()} | \
+             {"state_feat_q": Tensor(self.rng.standard_normal(STATE).astype(np.float32)).realize(),
+              "output_buffers": {"outputs": Tensor.zeros(OUT).contiguous().realize(), "next_state_feat_q": Tensor.zeros(STATE).contiguous().realize()}}
+    frames = Tensor(self.rng.integers(0, 256, (2, FRAME_SIZE), dtype=np.uint8)).realize()
+    tfm = Tensor(np.tile(np.eye(3, dtype=np.float32), (2, 1, 1))).realize()
+    path = os.path.join(self.tmp.name, "native_tinygrad.pkl")
+    part = compile_jit(native, model_inputs(warp(input_frame=frames, M_inv=tfm).realize()), "output_buffers")
+    extras = {"input_specs": {"new_img": ((2, 6, MODEL_H // 2, MODEL_W // 2), "|u1", "CPU"), "state_feat_q": (STATE, "<f4", "CPU")}
+              | {name: (shape, "<f4", "CPU") for name, shape in HOST.items()},
+              "output_specs": {"outputs": (OUT, "<f4", "CPU"), "next_state_feat_q": (STATE, "<f4", "CPU")},
+              "metadata": {"output_shapes": {"outputs": OUT, "next_state_feat_q": STATE}}}
+    write_bundle(path, {"run": part}, extras)
+
+    fused = load_model(path, cache=False, extend=functools.partial(frame_part, warp_path))
+    assert fused["run"].input_names == ["host", "state_feat_q"]
+    offsets, packed = pack_layout(HOST, FRAME_SIZE)
+    host = np.zeros(packed, np.uint8)
+    inputs = model_inputs(None)
+    for name, shape in ({"tfm": (2, 3, 3)} | HOST).items():
+      np.ndarray(shape, np.float32, host, offsets[name])[...] = tfm.numpy() if name == "tfm" else inputs[name].numpy()
+    host[offsets["frames"]:] = frames.numpy().ravel()
+    fused["run"](host=Tensor(host, device="NPY"), state_feat_q=inputs["state_feat_q"], output_buffers=inputs["output_buffers"])
+
+    expected = model_inputs(warp(input_frame=frames, M_inv=tfm).realize()) | {k: inputs[k] for k in ("state_feat_q",)}
+    native(**expected)
+    for name in ("outputs", "next_state_feat_q"):
+      assert np.array_equal(inputs["output_buffers"][name].numpy(), expected["output_buffers"][name].numpy()), name
+
+  def test_tinygrad_api_the_loader_reads(self):
+    import tinygrad.engine.jit as jit
+    from tinygrad.device import Buffer, TinyELF
+    from tinygrad.helpers import Target
+    from tinygrad.uop.ops import ParamArg, ProgramInfo, UOp
+    fields = {cls: {f.name for f in dataclasses.fields(cls)} for cls in (ProgramInfo, ParamArg, Target)}
+    assert fields[ProgramInfo] >= {"global_size", "local_size", "globals", "outs", "ins", "target"}, "ProgramInfo changed: update helpers._program_uop"
+    assert fields[ParamArg] >= {"slot", "dtype", "name", "image"}, "ParamArg changed: update helpers._program_uop"
+    assert fields[Target] >= {"device", "renderer", "arch"}, "Target changed: update the 'target' key in plain_artifact_compiler.serialize_jit"
+    assert "signature" in getattr(TinyELF, "__annotations__", {}) or hasattr(UOp, "kernel_params"), \
+      "kernel signatures moved: update plain_artifact_compiler.serialize_jit"
+    assert callable(getattr(UOp, "param", None)) and callable(getattr(UOp, "from_buffer", None)), "UOp.param/from_buffer: update helpers.PlainJit"
+    assert callable(getattr(UOp, "store_call", None)) and callable(getattr(UOp, "call", None)), "UOp.call/store_call: update helpers.PlainJit"
+    assert callable(getattr(Buffer, "view", None)) and callable(getattr(Buffer, "ensure_allocated", None)), "Buffer.view: update helpers._upload"
+    assert callable(getattr(jit, "compile_linear", None)) and callable(getattr(jit, "_prepare_jit_inputs", None)), "engine.jit: update helpers._Jit"
+    assert "expected_names" in inspect.signature(jit.CapturedJit).parameters, "CapturedJit: update helpers.PlainJit and plain_artifact_compiler.serialize_jit"

openpilot/sunnypilot/models/manager.py

@@ -34,8 +34,6 @@ TRANSIENT_HTTP_STATUS = frozenset({408, 429, 500, 502, 503, 504})
 REPORT_INTERVAL = 0.5  # seconds between progress publications
 # byte ranges count encoded bytes but iter_content yields decoded ones, so ask for an unencoded body
 NO_COMPRESSION = {"Accept-Encoding": "identity"}
-SPEED_SMOOTHING = 0.7  # weight of the previous speed sample in the published speed
-SPEED_FLOOR = 0.05 * 1024 ** 2  # bytes/s; anything slower would only display as 0.0 MB/s, so it reads as no rate
 
 
 class DownloadCancelled(Exception):
@@ -156,7 +154,6 @@ class ModelManagerSP:
         artifact.downloadProgress.status = source_artifact.downloadProgress.status
         artifact.downloadProgress.progress = source_artifact.downloadProgress.progress
         artifact.downloadProgress.eta = source_artifact.downloadProgress.eta
-        artifact.downloadProgress.speed = source_artifact.downloadProgress.speed
 
   def _calculate_eta(self, filename: str, progress: float) -> int:
     if filename not in self._download_start_times or progress <= 0:
@@ -170,43 +167,28 @@ class ModelManagerSP:
     eta = total_estimated_time - elapsed_time
     return max(1, int(eta))  # Return at least 1 second if download is ongoing
 
-  def _set_progress(self, artifact, status, progress: float, eta: int = 0, speed: float = 0.0) -> None:
+  def _set_progress(self, artifact, status, progress: float, eta: int = 0) -> None:
     artifact.downloadProgress.status = status
     artifact.downloadProgress.progress = progress
     artifact.downloadProgress.eta = eta
-    artifact.downloadProgress.speed = speed
     self._sync_artifact_progress(artifact)
     self._report_status()
 
-  def _publish_progress(self, artifact, done_bytes: int, total: int, speed: float) -> None:
+  def _publish_progress(self, artifact, done_bytes: int, total: int) -> None:
     # held at 99 until the file passes its hash check
     progress = min(99.0, done_bytes / total * 100) if total > 0 else 0.0
-    if speed > 0 and total > 0:
-      eta = max(1, int((total - done_bytes) / speed))
-    else:
-      eta = self._calculate_eta(artifact.fileName, progress)
-    self._set_progress(artifact, custom.ModelManagerSP.DownloadStatus.downloading, progress, eta, speed)
+    eta = self._calculate_eta(artifact.fileName, progress)
+    self._set_progress(artifact, custom.ModelManagerSP.DownloadStatus.downloading, progress, eta)
 
-  async def _report_until_done(self, tasks: list[asyncio.Future], artifact, progress: _Progress, total: int,
-                               started: tuple[int, float]) -> None:
+  async def _report_until_done(self, tasks: list[asyncio.Future], artifact, progress: _Progress, total: int) -> None:
     pending = set(tasks)
-    last_bytes, last_time = started
-    speed = 0.0
     while pending:
       done, pending = await asyncio.wait(pending, timeout=REPORT_INTERVAL)
       for task in done:
         task.result()  # re-raises a worker failure
       if self._download_interrupted():
         raise DownloadCancelled("Download cancelled")
-      now = time.monotonic()
-      done_bytes = progress.snapshot()
-      if (dt := now - last_time) > 0:
-        instant = max(0.0, (done_bytes - last_bytes) / dt)  # bytes/s this tick; clamped since retried pieces can lower the byte count
-        speed = instant if speed == 0 else SPEED_SMOOTHING * speed + (1 - SPEED_SMOOTHING) * instant
-        if speed < SPEED_FLOOR:  # a stall decays toward 0 without reaching it, and a near-0 speed overflows the eta
-          speed = 0.0
-      last_time, last_bytes = now, done_bytes
-      self._publish_progress(artifact, done_bytes, total, speed)
+      self._publish_progress(artifact, progress.snapshot(), total)
 
   async def _download_file(self, url: str, path: str, artifact) -> None:
     self._download_start_times[artifact.fileName] = time.monotonic()
@@ -217,13 +199,12 @@ class ModelManagerSP:
     await loop.run_in_executor(None, _prepare_target, path, total)
     progress = _Progress()
     cancel = threading.Event()
-    started = progress.snapshot(), time.monotonic()  # before any worker can land bytes
 
     with ThreadPoolExecutor(max_workers=MAX_CONCURRENT_PIECES) as pool:
       tasks = [loop.run_in_executor(pool, _fetch_piece, url, path, i, start, end, progress, cancel, self._block_size)
                for i, (start, end) in enumerate(pieces)]
       try:
-        await self._report_until_done(tasks, artifact, progress, total, started)
+        await self._report_until_done(tasks, artifact, progress, total)
       except BaseException as e:
         cancel.set()
         if isinstance(e, DownloadCancelled):
@@ -266,7 +247,6 @@ class ModelManagerSP:
       self._download_start_times.pop(artifact.fileName, None)
       artifact.downloadProgress.status = status.failed
       artifact.downloadProgress.eta = 0
-      artifact.downloadProgress.speed = 0
       self._sync_artifact_progress(artifact)
       if self.selected_bundle:
         self.selected_bundle.status = status.failed
@@ -279,7 +259,6 @@ class ModelManagerSP:
         os.remove(full_path)
       artifact.downloadProgress.status = status.failed
       artifact.downloadProgress.eta = 0
-      artifact.downloadProgress.speed = 0
       self._sync_artifact_progress(artifact)
       if self.selected_bundle:
         self.selected_bundle.status = status.failed
@@ -322,7 +301,6 @@ class ModelManagerSP:
           artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.cached
           artifact.downloadProgress.progress = 100
           artifact.downloadProgress.eta = 0
-          artifact.downloadProgress.speed = 0
         else:
           seen_artifacts.add(artifact.fileName)
           await self._process_artifact(artifact, destination_path)

openpilot/sunnypilot/models/tests/test_manager_download.py

@@ -6,7 +6,6 @@ See the LICENSE.md file in the root directory for more details.
 """
 
 import asyncio
-import concurrent.futures
 import contextlib
 import dataclasses
 import hashlib
@@ -130,13 +129,6 @@ def threaded_server(handler):
     thread.join()
 
 
-class InlineExecutor(concurrent.futures.Executor):
-  def submit(self, fn, /, *args, **kwargs):
-    future: concurrent.futures.Future = concurrent.futures.Future()
-    future.set_result(fn(*args, **kwargs))  # the piece lands before the reporter starts
-    return future
-
-
 class ManagerDownloadTestBase(OpenpilotTestCase):
   def setUp(self):
     super().setUp()
@@ -147,7 +139,7 @@ class ManagerDownloadTestBase(OpenpilotTestCase):
     self.addCleanup(self._tmp.cleanup)
     self.dest = self._tmp.name
 
-    for name, value in (('PIECE_SIZE', PIECE_SIZE), ('REPORT_INTERVAL', 0.05), ('PIECE_BACKOFF', 0.01), ('SPEED_FLOOR', 100)):
+    for name, value in (('PIECE_SIZE', PIECE_SIZE), ('REPORT_INTERVAL', 0.05), ('PIECE_BACKOFF', 0.01)):
       self.enterContext(mock.patch.object(manager_module, name, value))
 
     self.reported: list[float] = []
@@ -237,31 +229,6 @@ class TestManagerDownload(ManagerDownloadTestBase):
     assert self.reported and self.reported == sorted(self.reported), "progress only rises"
     assert max(self.reported) <= 99.0, "progress holds below 100 until the hash check"
     assert artifact.fileName not in self.manager._download_start_times
-    assert artifact.downloadProgress.speed > 0, "a running download shows its speed"
-
-  def test_speed_counts_bytes_landed_before_the_first_report(self):
-    self.enterContext(mock.patch.object(manager_module, 'ThreadPoolExecutor', lambda max_workers: InlineExecutor()))
-    artifact = self.download_file()
-    assert artifact.downloadProgress.speed > 0
-
-  def test_eta_comes_from_speed(self):
-    artifact = self.make_artifact()
-    self.manager._publish_progress(artifact, done_bytes=400, total=1000, speed=100)
-    assert artifact.downloadProgress.eta == 6
-
-  def test_stalled_speed_drops_to_zero(self):
-    stall_event = self.stall(0)
-    seen_speed = threading.Event()
-
-    def release_once_zero(*args):
-      if self.artifact.downloadProgress.speed > 0:
-        seen_speed.set()
-      elif seen_speed.is_set():
-        stall_event.set()
-    self.pm.send.side_effect = release_once_zero
-    self.download_file()
-    assert self.server.stall_released_by_event is True, "the stalled speed never reached exactly 0"
-    assert self.artifact.downloadProgress.speed > 0, "the speed must recover once data flows again"
 
   def test_pieces_download_in_parallel(self):
     stall_event = self.stall(0)
@@ -336,8 +303,7 @@ class TestProcessArtifact(ManagerDownloadTestBase):
         self.download_bundle(source)
         assert ACTIVE_BUNDLE_KEYS[source] in store and ACTIVE_BUNDLE_KEYS[other] not in store
         assert self.manager.selected_bundle.status == ds.downloaded
-        assert self.artifact.downloadProgress.progress == 100
-        assert self.artifact.downloadProgress.eta == 0 and self.artifact.downloadProgress.speed == 0
+        assert self.artifact.downloadProgress.progress == 100 and self.artifact.downloadProgress.eta == 0
         assert self.read_path() == WHOLE_BODY
         os.remove(self.path)