Update on "unbreak mypy torch/quantization"

Summary:

Somehow `mypy torch/quantization` got broken in the past couple of days:
https://gist.github.com/vkuzo/07af454246f0a68e6fa8929beeec7e0d
.  I didn't see any relevant PRs other than
#47725, which doesn't seem
related. The error doesn't seem real, as the arguments to
`_cudnn_rnn_flatten_weight` seem correct. For now,
ignoring the failure so we have a clean `mypy` run on
`torch/quantization`.

Test Plan:

```
mypy torch/quantization
```

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: [D25616972](https://our.internmc.facebook.com/intern/diff/D25616972)

[ghstack-poisoned]

.circleci/config.yml

@@ -639,7 +639,7 @@ jobs:
           export CIRCLE_JOB="$CIRCLE_JOB"
           export CIRCLE_WORKFLOW_ID="$CIRCLE_WORKFLOW_ID"
           cd workspace
-          python test/print_test_stats.py test
+          python test/print_test_stats.py --upload-to-s3 test
           EOL
           echo "(cat docker_commands.sh | docker exec -u jenkins -i "$id" bash) 2>&1" > command.sh
           unbuffer bash command.sh | ts

.circleci/docker/common/install_conda.sh

@@ -109,6 +109,7 @@ if [ -n "$ANACONDA_PYTHON_VERSION" ]; then
     numba \
     llvmlite \
     unittest-xml-reporting \
+    boto3==1.16.34 \
     coverage \
     hypothesis==4.53.2 \
     mypy==0.770 \

.circleci/verbatim-sources/job-specs/pytorch-job-specs.yml

@@ -201,7 +201,7 @@ jobs:
           export CIRCLE_JOB="$CIRCLE_JOB"
           export CIRCLE_WORKFLOW_ID="$CIRCLE_WORKFLOW_ID"
           cd workspace
-          python test/print_test_stats.py test
+          python test/print_test_stats.py --upload-to-s3 test
           EOL
           echo "(cat docker_commands.sh | docker exec -u jenkins -i "$id" bash) 2>&1" > command.sh
           unbuffer bash command.sh | ts

CONTRIBUTING.md

@@ -754,7 +754,7 @@ than Linux, which are worth keeping in mind when fixing these problems.
 1. Symbols are NOT exported by default on Windows; instead, you have to explicitly
    mark a symbol as exported/imported in a header file with `__declspec(dllexport)` /
    `__declspec(dllimport)`. We have codified this pattern into a set of macros
-   which follow the convention `*_API`, e.g., `CAFFE2_API` inside Caffe2 and ATen.
+   which follow the convention `*_API`, e.g., `TORCH_API` inside Caffe2, Aten and Torch.
    (Every separate shared library needs a unique macro name, because symbol visibility
    is on a per shared library basis. See c10/macros/Macros.h for more details.)
 

aten/src/ATen/CPUGeneratorImpl.h

@@ -7,7 +7,7 @@
 
 namespace at {
 
-struct CAFFE2_API CPUGeneratorImpl : public c10::GeneratorImpl {
+struct TORCH_API CPUGeneratorImpl : public c10::GeneratorImpl {
   // Constructors
   CPUGeneratorImpl(uint64_t seed_in = default_rng_seed_val);
   ~CPUGeneratorImpl() = default;
@@ -36,8 +36,8 @@ struct CAFFE2_API CPUGeneratorImpl : public c10::GeneratorImpl {
 
 namespace detail {
 
-CAFFE2_API const Generator& getDefaultCPUGenerator();
-CAFFE2_API Generator createCPUGenerator(uint64_t seed_val = default_rng_seed_val);
+TORCH_API const Generator& getDefaultCPUGenerator();
+TORCH_API Generator createCPUGenerator(uint64_t seed_val = default_rng_seed_val);
 
 } // namespace detail
 

aten/src/ATen/Context.h

@@ -21,7 +21,7 @@ namespace at {
 
 class Tensor;
 
-class CAFFE2_API Context {
+class TORCH_API Context {
  public:
   Context();
 
@@ -225,13 +225,13 @@ class CAFFE2_API Context {
   std::unique_ptr<THHState, void(*)(THHState*)> thh_state;
 };
 
-CAFFE2_API Context& globalContext();
+TORCH_API Context& globalContext();
 
 static inline void init() {
   globalContext();
 }
 
-CAFFE2_API Allocator* getCPUAllocator();
+TORCH_API Allocator* getCPUAllocator();
 
 static inline DeprecatedTypeProperties& getDeprecatedTypeProperties(Backend p, ScalarType s) {
   return globalDeprecatedTypePropertiesRegistry().getDeprecatedTypeProperties(

aten/src/ATen/DLConvertor.h

@@ -10,10 +10,10 @@
 
 namespace at {
 
-CAFFE2_API ScalarType toScalarType(const DLDataType& dtype);
-CAFFE2_API DLManagedTensor* toDLPack(const Tensor& src);
-CAFFE2_API Tensor fromDLPack(const DLManagedTensor* src);
-CAFFE2_API DLDataType getDLDataType(const Tensor& t);
-CAFFE2_API DLContext getDLContext(const Tensor& tensor, const int64_t& device_id);
+TORCH_API ScalarType toScalarType(const DLDataType& dtype);
+TORCH_API DLManagedTensor* toDLPack(const Tensor& src);
+TORCH_API Tensor fromDLPack(const DLManagedTensor* src);
+TORCH_API DLDataType getDLDataType(const Tensor& t);
+TORCH_API DLContext getDLContext(const Tensor& tensor, const int64_t& device_id);
 
 } //namespace at

aten/src/ATen/DynamicLibrary.h

@@ -8,11 +8,11 @@ namespace at {
 struct DynamicLibrary {
   AT_DISALLOW_COPY_AND_ASSIGN(DynamicLibrary);
 
-  CAFFE2_API DynamicLibrary(const char* name);
+  TORCH_API DynamicLibrary(const char* name);
 
-  CAFFE2_API void* sym(const char* name);
+  TORCH_API void* sym(const char* name);
 
-  CAFFE2_API ~DynamicLibrary();
+  TORCH_API ~DynamicLibrary();
 
  private:
   void* handle = nullptr;

aten/src/ATen/ExpandUtils.h

@@ -9,14 +9,14 @@
 
 namespace at {
 
-CAFFE2_API std::vector<int64_t> infer_size(IntArrayRef a, IntArrayRef b);
-CAFFE2_API std::tuple<std::vector<int64_t>, std::vector<int64_t>>
+TORCH_API std::vector<int64_t> infer_size(IntArrayRef a, IntArrayRef b);
+TORCH_API std::tuple<std::vector<int64_t>, std::vector<int64_t>>
 inferExpandGeometry(
     IntArrayRef tensor_sizes,
     IntArrayRef tensor_strides,
     IntArrayRef sizes);
 
-CAFFE2_API std::vector<int64_t> infer_dense_strides(
+TORCH_API std::vector<int64_t> infer_dense_strides(
     IntArrayRef tensor_sizes,
     IntArrayRef tensor_strides);
 

aten/src/ATen/MemoryOverlap.h

@@ -15,19 +15,19 @@ enum class MemOverlap { NO, YES, TOO_HARD };
 
 enum class MemOverlapStatus { FULL, PARTIAL, NO, TOO_HARD };
 
-CAFFE2_API MemOverlap has_internal_overlap(const Tensor& t);
-CAFFE2_API MemOverlap has_internal_overlap(TensorImpl* t);
+TORCH_API MemOverlap has_internal_overlap(const Tensor& t);
+TORCH_API MemOverlap has_internal_overlap(TensorImpl* t);
 
-CAFFE2_API void assert_no_internal_overlap(const Tensor& t);
-CAFFE2_API void assert_no_internal_overlap(TensorImpl* t);
+TORCH_API void assert_no_internal_overlap(const Tensor& t);
+TORCH_API void assert_no_internal_overlap(TensorImpl* t);
 
-CAFFE2_API MemOverlapStatus get_overlap_status(const Tensor& a, const Tensor& b);
-CAFFE2_API MemOverlapStatus get_overlap_status(TensorImpl* a, TensorImpl* b);
+TORCH_API MemOverlapStatus get_overlap_status(const Tensor& a, const Tensor& b);
+TORCH_API MemOverlapStatus get_overlap_status(TensorImpl* a, TensorImpl* b);
 
-CAFFE2_API void assert_no_partial_overlap(const Tensor& a, const Tensor& b);
+TORCH_API void assert_no_partial_overlap(const Tensor& a, const Tensor& b);
 void assert_no_partial_overlap(TensorImpl* a, TensorImpl* b);
 
-CAFFE2_API void assert_no_overlap(const Tensor& a, const Tensor& b);
-CAFFE2_API void assert_no_overlap(TensorImpl* a, TensorImpl* b);
+TORCH_API void assert_no_overlap(const Tensor& a, const Tensor& b);
+TORCH_API void assert_no_overlap(TensorImpl* a, TensorImpl* b);
 
 }

aten/src/ATen/NamedTensorUtils.h

@@ -17,8 +17,8 @@ inline bool has_names(TensorList tensors) {
 
 // Converts dim to an positional index. Errors if `dim` cannot be used to
 // refer to any dimension of tensor.
-CAFFE2_API int64_t dimname_to_position(const Tensor& tensor, Dimname dim);
-CAFFE2_API std::vector<int64_t> dimnames_to_positions(const Tensor& tensor, DimnameList dims);
+TORCH_API int64_t dimname_to_position(const Tensor& tensor, Dimname dim);
+TORCH_API std::vector<int64_t> dimnames_to_positions(const Tensor& tensor, DimnameList dims);
 
 // Unifies two DimnameList to produce a third. This is useful for implementing
 // the named inference rule for binary broadcasting operations like add.
@@ -28,7 +28,7 @@ CAFFE2_API std::vector<int64_t> dimnames_to_positions(const Tensor& tensor, Dimn
 // 2) Check misaligned: If a name `n` is in `names`, then it must appear at
 //    the same index from the right in other.
 // 3) The output names are obtained by unifying the names individually from the right.
-CAFFE2_API std::vector<Dimname>
+TORCH_API std::vector<Dimname>
 unify_from_right(DimnameList names, DimnameList other, const char* action = "broadcast");
 
 [[noreturn]] inline void reportNYIDimnameOverload(const char* op_name) {
@@ -75,50 +75,50 @@ namespace namedinference {
 // `names` can be empty; see [NOTE] Writing name inference rules
 // If `names` is not empty, `names.size()` should equal `result.dim()`.
 // When in doubt, use this overload instead of the others.
-CAFFE2_API Tensor& propagate_names_if_nonempty(
+TORCH_API Tensor& propagate_names_if_nonempty(
     Tensor& result,
     DimnameList maybe_names,
     bool validate_names = false);
 
 // Propagates `names` to `result`. Only use this if we are certain that there are
 // names to propagate (that names is not empty).
-CAFFE2_API Tensor& propagate_names(
+TORCH_API Tensor& propagate_names(
     Tensor& result,
     DimnameList names,
     bool validate_names = false);
 
 // Propagates all names from src to result.
-CAFFE2_API void propagate_names(Tensor& result, const Tensor& src);
+TORCH_API void propagate_names(Tensor& result, const Tensor& src);
 
 // Propagates all names except for those at the excluded_idxs.
-CAFFE2_API void propagate_names_except(Tensor& result, const Tensor& src, IntArrayRef excluded_idxs);
+TORCH_API void propagate_names_except(Tensor& result, const Tensor& src, IntArrayRef excluded_idxs);
 
 // Used for reduction ops that have a `keepdim` arg.
-CAFFE2_API void propagate_names_for_reduction(Tensor& result, const Tensor& src, IntArrayRef excluded_idxs, bool keepdim);
+TORCH_API void propagate_names_for_reduction(Tensor& result, const Tensor& src, IntArrayRef excluded_idxs, bool keepdim);
 
-CAFFE2_API void propagate_names_for_expand(Tensor& result, const Tensor& self);
+TORCH_API void propagate_names_for_expand(Tensor& result, const Tensor& self);
 
-CAFFE2_API std::vector<Dimname> compute_cat_outnames(TensorList tensors);
+TORCH_API std::vector<Dimname> compute_cat_outnames(TensorList tensors);
 
-CAFFE2_API std::vector<Dimname> compute_broadcast_outnames(
+TORCH_API std::vector<Dimname> compute_broadcast_outnames(
     const Tensor& self,
     const Tensor& other);
 
-CAFFE2_API std::vector<Dimname> broadcast_to_outnames(
+TORCH_API std::vector<Dimname> broadcast_to_outnames(
     const Tensor& tensor,
     const Tensor& reference_tensor,
     const char* op_name);
 
-CAFFE2_API std::vector<Dimname> compute_matmul_outnames(const Tensor& self, const Tensor& other);
+TORCH_API std::vector<Dimname> compute_matmul_outnames(const Tensor& self, const Tensor& other);
 
-CAFFE2_API std::vector<Dimname> compute_cdist_outnames(const Tensor& self, const Tensor& other);
+TORCH_API std::vector<Dimname> compute_cdist_outnames(const Tensor& self, const Tensor& other);
 
-CAFFE2_API std::vector<Dimname> compute_bmm_outnames(
+TORCH_API std::vector<Dimname> compute_bmm_outnames(
     Tensor& result,
     const Tensor& self,
     const Tensor& other);
 
-CAFFE2_API std::vector<Dimname> compute_squeeze_outnames(const Tensor& tensor);
+TORCH_API std::vector<Dimname> compute_squeeze_outnames(const Tensor& tensor);
 
 std::vector<Dimname> compute_diagonal_outnames(
     const Tensor& tensor,
@@ -127,40 +127,40 @@ std::vector<Dimname> compute_diagonal_outnames(
 
 // TensorImpl* overloads for Legacy TH/THC code. Use these sparingly.
 
-CAFFE2_API TensorImpl* propagate_names_if_nonempty(
+TORCH_API TensorImpl* propagate_names_if_nonempty(
     TensorImpl* result,
     DimnameList maybe_names,
     bool validate_names = false);
 
-CAFFE2_API TensorImpl* propagate_names(
+TORCH_API TensorImpl* propagate_names(
     TensorImpl* result,
     DimnameList names,
     bool validate_names = false);
 
-CAFFE2_API void propagate_names(TensorImpl* result, /*const */TensorImpl* src);
+TORCH_API void propagate_names(TensorImpl* result, /*const */TensorImpl* src);
 
 // result = m1 @ m2 + bias
-CAFFE2_API void propagate_names_for_addmm(
+TORCH_API void propagate_names_for_addmm(
     Tensor& result,
     const Tensor& m1,
     const Tensor& m2,
     const Tensor& bias);
 
-CAFFE2_API void propagate_names_for_addmv(
+TORCH_API void propagate_names_for_addmv(
     Tensor& result,
     const Tensor& mat,
     const Tensor& vec,
     const Tensor& bias);
 
-CAFFE2_API void check_names_for_dot(TensorImpl* vec1, TensorImpl* vec2);
+TORCH_API void check_names_for_dot(TensorImpl* vec1, TensorImpl* vec2);
 
-CAFFE2_API std::vector<Dimname> compute_baddbmm_outnames(
+TORCH_API std::vector<Dimname> compute_baddbmm_outnames(
     Tensor& result,
     const Tensor& self,
     const Tensor& other,
     const Tensor& bias);
 
-CAFFE2_API bool are_names_equal(TensorImpl* self, TensorImpl* other);
+TORCH_API bool are_names_equal(TensorImpl* self, TensorImpl* other);
 
 } // namespace namedinference
 

aten/src/ATen/OpaqueTensorImpl.h

@@ -17,7 +17,7 @@ namespace at {
 // "shallow copy" in order to add support.
 
 template <typename OpaqueHandle>
-struct CAFFE2_API OpaqueTensorImpl : public TensorImpl {
+struct TORCH_API OpaqueTensorImpl : public TensorImpl {
   // public constructor for now...
   OpaqueTensorImpl(
       at::DispatchKeySet key_set,

aten/src/ATen/PTThreadPool.h

@@ -5,7 +5,7 @@
 
 namespace at {
 
-class CAFFE2_API PTThreadPool : public c10::ThreadPool {
+class TORCH_API PTThreadPool : public c10::ThreadPool {
 public:
   explicit PTThreadPool(
       int pool_size,

aten/src/ATen/Parallel.h

@@ -10,25 +10,25 @@ inline int64_t divup(int64_t x, int64_t y) {
 }
 
 // Called during new thread initialization
-CAFFE2_API void init_num_threads();
+TORCH_API void init_num_threads();
 
 // Sets the number of threads to be used in parallel region
-CAFFE2_API void set_num_threads(int);
+TORCH_API void set_num_threads(int);
 
 // Returns the maximum number of threads that may be used in a parallel region
-CAFFE2_API int get_num_threads();
+TORCH_API int get_num_threads();
 
 // Returns the current thread number (starting from 0)
 // in the current parallel region, or 0 in the sequential region
-CAFFE2_API int get_thread_num();
+TORCH_API int get_thread_num();
 
 // Checks whether the code runs in parallel region
-CAFFE2_API bool in_parallel_region();
+TORCH_API bool in_parallel_region();
 
 namespace internal {
 
 // Initialise num_threads lazily at first parallel call
-inline CAFFE2_API void lazy_init_num_threads() {
+inline TORCH_API void lazy_init_num_threads() {
   thread_local bool init = false;
   if (C10_UNLIKELY(!init)) {
     at::init_num_threads();
@@ -110,29 +110,29 @@ inline scalar_t parallel_reduce(
     const SF& sf);
 
 // Returns a detailed string describing parallelization settings
-CAFFE2_API std::string get_parallel_info();
+TORCH_API std::string get_parallel_info();
 
 // Sets number of threads used for inter-op parallelism
-CAFFE2_API void set_num_interop_threads(int);
+TORCH_API void set_num_interop_threads(int);
 
 // Returns the number of threads used for inter-op parallelism
-CAFFE2_API int get_num_interop_threads();
+TORCH_API int get_num_interop_threads();
 
 // Launches inter-op parallel task
-CAFFE2_API void launch(std::function<void()> func);
+TORCH_API void launch(std::function<void()> func);
 namespace internal {
 void launch_no_thread_state(std::function<void()> fn);
 } // namespace internal
 
 // Launches intra-op parallel task
-CAFFE2_API void intraop_launch(std::function<void()> func);
+TORCH_API void intraop_launch(std::function<void()> func);
 
 // Launches intra-op parallel task, returns a future
-CAFFE2_API std::shared_ptr<c10::ivalue::Future> intraop_launch_future(
+TORCH_API std::shared_ptr<c10::ivalue::Future> intraop_launch_future(
     std::function<void()> func);
 
 // Returns number of intra-op threads used by default
-CAFFE2_API int intraop_default_num_threads();
+TORCH_API int intraop_default_num_threads();
 
 } // namespace at
 

aten/src/ATen/ParallelNative.h

@@ -22,7 +22,7 @@ inline std::tuple<size_t, size_t> calc_num_tasks_and_chunk_size(
   return std::make_tuple(num_tasks, chunk_size);
 }
 
-CAFFE2_API void _parallel_run(
+TORCH_API void _parallel_run(
   const int64_t begin,
   const int64_t end,
   const int64_t grain_size,

aten/src/ATen/SparseTensorImpl.h

@@ -5,7 +5,7 @@
 #include <c10/util/Exception.h>
 
 namespace at {
-struct CAFFE2_API SparseTensorImpl : public TensorImpl {
+struct TORCH_API SparseTensorImpl : public TensorImpl {
   // Stored in COO format, indices + values.
 
   // INVARIANTS: