[quant][graphmode][fx][fix] Fix quantization for tuple arguments

[jerryzh168]

Stack from ghstack:

• -> [quant][graphmode][fx][fix] Fix quantization for tuple arguments #63376

Summary:
Previously when tuple is an argument for a quantizable op it would be transformed to a list by mistake,
this PR fixes that.

Test Plan:
python test/test_quantization.py TestQuantizeFx.test_preserve_tuple

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: D30357642

[facebook-github-bot]

🔗 Helpful links

• 🧪 See artifacts and rendered test results at hud.pytorch.org/pr/63376
• 📄 Preview docs built from this PR

💊 CI failures summary and remediations

As of commit f08bf18 (more details on the Dr. CI page):

---

• 2/2 failures possibly* introduced in this PR
  • 1/2 non-scanned failure(s)

---

🕵️ 1 new failure recognized by patterns

The following CI failures do not appear to be due to upstream breakages:

pytorch_linux_xenial_py3_clang7_asan_test2 (1/1)

Step: "Run tests" (full log | diagnosis details | 🔁 rerun)

Aug 17 03:37:44 test_remote_message_script_de...yUniqueId(created_on=0, local_id=0) to be created.

Aug 17 03:37:03 frame #13: <unknown function> + 0x198a6280 (0x7f4c71973280 in /opt/conda/lib/python3.6/site-packages/torch/lib/libtorch_cpu.so)
Aug 17 03:37:03 frame #14: c10::ThreadPool::main_loop(unsigned long) + 0x7f1 (0x7f4c4ebbab91 in /opt/conda/lib/python3.6/site-packages/torch/lib/libc10.so)
Aug 17 03:37:03 frame #15: <unknown function> + 0xb8c80 (0x7f4c9b223c80 in /usr/lib/x86_64-linux-gnu/libstdc++.so.6)
Aug 17 03:37:03 frame #16: <unknown function> + 0x76ba (0x7f4c9b8be6ba in /lib/x86_64-linux-gnu/libpthread.so.0)
Aug 17 03:37:03 frame #17: clone + 0x6d (0x7f4c9b5f451d in /lib/x86_64-linux-gnu/libc.so.6)
Aug 17 03:37:03 
Aug 17 03:37:03 ok (7.202s)
Aug 17 03:37:14   test_remote_message_dropped_pickle (__main__.FaultyFaultyAgentRpcTestWithSpawn) ... ok (11.109s)
Aug 17 03:37:26   test_remote_message_dropped_pickle_to_self (__main__.FaultyFaultyAgentRpcTestWithSpawn) ... ok (11.308s)
Aug 17 03:37:36   test_remote_message_script_delay_timeout (__main__.FaultyFaultyAgentRpcTestWithSpawn) ... ok (10.513s)
Aug 17 03:37:44   test_remote_message_script_delay_timeout_to_self (__main__.FaultyFaultyAgentRpcTestWithSpawn) ... [E request_callback_no_python.cpp:559] Received error while processing request type 260: falseINTERNAL ASSERT FAILED at "/var/lib/jenkins/workspace/torch/csrc/distributed/rpc/rref_context.cpp":387, please report a bug to PyTorch. Expected OwnerRRef with id GloballyUniqueId(created_on=0, local_id=0) to be created.
Aug 17 03:37:44 Exception raised from getOwnerRRef at /var/lib/jenkins/workspace/torch/csrc/distributed/rpc/rref_context.cpp:387 (most recent call first):
Aug 17 03:37:44 frame #0: <unknown function> + 0x1a231c (0x7f676fb9131c in /opt/conda/lib/python3.6/site-packages/torch/lib/libc10.so)
Aug 17 03:37:44 frame #1: std::function<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > ()>::operator()() const + 0x6d (0x7f67915e3d9d in /opt/conda/lib/python3.6/site-packages/torch/lib/libtorch_cpu.so)
Aug 17 03:37:44 frame #2: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >) + 0x160 (0x7f676fb8f800 in /opt/conda/lib/python3.6/site-packages/torch/lib/libc10.so)
Aug 17 03:37:44 frame #3: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) + 0x18a (0x7f676fb8a66a in /opt/conda/lib/python3.6/site-packages/torch/lib/libc10.so)
Aug 17 03:37:44 frame #4: c10::detail::torchInternalAssertFail(char const*, char const*, unsigned int, char const*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&) + 0x115 (0x7f676fb8ad75 in /opt/conda/lib/python3.6/site-packages/torch/lib/libc10.so)
Aug 17 03:37:44 frame #5: torch::distributed::rpc::RRefContext::getOwnerRRef(torch::distributed::rpc::GloballyUniqueId const&, bool) + 0xd62 (0x7f67928676f2 in /opt/conda/lib/python3.6/site-packages/torch/lib/libtorch_cpu.so)
Aug 17 03:37:44 frame #6: torch::distributed::rpc::RequestCallbackNoPython::assignOwnerRRef(torch::distributed::rpc::GloballyUniqueId const&, torch::distributed::rpc::GloballyUniqueId const&, c10::intrusive_ptr<c10::ivalue::Future, c10::detail::intrusive_target_default_null_type<c10::ivalue::Future> >) const + 0x223 (0x7f679282c443 in /opt/conda/lib/python3.6/site-packages/torch/lib/libtorch_cpu.so)
Aug 17 03:37:44 frame #7: torch::distributed::rpc::RequestCallbackImpl::processScriptRemoteCall(torch::distributed::rpc::RpcCommandBase&, std::vector<c10::Stream, std::allocator<c10::Stream> >) const + 0x8e3 (0x7f67b4fdac23 in /opt/conda/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
Aug 17 03:37:44 frame #8: torch::distributed::rpc::RequestCallbackNoPython::processRpc(torch::distributed::rpc::RpcCommandBase&, torch::distributed::rpc::MessageType const&, std::vector<c10::Stream, std::allocator<c10::Stream> >) const + 0x78d (0x7f67928295cd in /opt/conda/lib/python3.6/site-packages/torch/lib/libtorch_cpu.so)

---

1 job timed out:

• pytorch_linux_xenial_py3_clang7_asan_test2

---

ci.pytorch.org: 1 failed

• Failed: pr/pytorch-linux-bionic-rocm4.2-py3.6

---

This comment was automatically generated by Dr. CI (expand for details).

Follow this link to opt-out of these comments for your Pull Requests.

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

[jerryzh168]

@jerryzh168 has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

[jerryzh168]

@jerryzh168 has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

[facebook-github-bot]

This pull request has been merged in cd5e9dc.