From 9420f4e3238bcf03ee1b91bf6565052efcf2fd5b Mon Sep 17 00:00:00 2001
From: Michael Gschwind <61328285+mikekgfb@users.noreply.github.com>
Date: Wed, 11 Dec 2024 09:32:25 -0800
Subject: [PATCH 1/3] bandaid for run-readme-pr-macos.yml incorrectly loading
 to MPS

as per #1416 torchchat on hosts without MPS (which is all github hosts which use kvm to virtualize MacOS, but not MPS) should choose CPU as "fast" device.  The logic is present (see discussion in #1416 ), but either not fully functional (that would be the easier one to fix, just print the result of get_device_str and fix the code!) or specifically ignored on load in torch/serialization.py (If this is the case, we're effectively looking at a core PyTorch issue....)

In the meantime, this bandaid just forces the use of CPU on MacOS tests, to make MacOS tests run on CPU -- labeit hsortcircuiting test/execution of the "fast" device logic.  Not ideal, but some testing beats no testing.
---
 .github/workflows/run-readme-pr-macos.yml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/run-readme-pr-macos.yml b/.github/workflows/run-readme-pr-macos.yml
index 64afe2247..b11251132 100644
--- a/.github/workflows/run-readme-pr-macos.yml
+++ b/.github/workflows/run-readme-pr-macos.yml
@@ -33,7 +33,7 @@ jobs:
           sysctl machdep.cpu.core_count
           echo "::endgroup::"
 
-          .ci/scripts/run-docs readme
+          TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs readme
   
           echo "::group::Completion"
           echo "tests complete"
@@ -68,7 +68,7 @@ jobs:
           sysctl machdep.cpu.core_count
           echo "::endgroup::"
 
-          .ci/scripts/run-docs quantization
+          TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs quantization
   
           echo "::group::Completion"
           echo "tests complete"
@@ -103,7 +103,7 @@ jobs:
           sysctl machdep.cpu.core_count
           echo "::endgroup::"
 
-          .ci/scripts/run-docs gguf
+          TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs gguf
 
           echo "::group::Completion"
           echo "tests complete"
@@ -137,7 +137,7 @@ jobs:
           sysctl machdep.cpu.core_count
           echo "::endgroup::"
 
-          .ci/scripts/run-docs advanced
+          TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs advanced
 
           echo "::group::Completion"
           echo "tests complete"

From 63f83074deac66ef38ba6019a24289f6a2a27037 Mon Sep 17 00:00:00 2001
From: Michael Gschwind <61328285+mikekgfb@users.noreply.github.com>
Date: Wed, 11 Dec 2024 09:45:04 -0800
Subject: [PATCH 2/3] Update run-readme-pr-macos.yml

Add informational message to MacOS CPU tests
---
 .github/workflows/run-readme-pr-macos.yml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/.github/workflows/run-readme-pr-macos.yml b/.github/workflows/run-readme-pr-macos.yml
index b11251132..67c7a6cca 100644
--- a/.github/workflows/run-readme-pr-macos.yml
+++ b/.github/workflows/run-readme-pr-macos.yml
@@ -33,6 +33,7 @@ jobs:
           sysctl machdep.cpu.core_count
           echo "::endgroup::"
 
+          echo "using workaround for #1416 and #1315 by setting torchchat device explicitly"
           TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs readme
   
           echo "::group::Completion"
@@ -68,6 +69,7 @@ jobs:
           sysctl machdep.cpu.core_count
           echo "::endgroup::"
 
+          echo "using workaround for #1416 and #1315 by setting torchchat device explicitly"
           TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs quantization
   
           echo "::group::Completion"
@@ -103,6 +105,7 @@ jobs:
           sysctl machdep.cpu.core_count
           echo "::endgroup::"
 
+          echo "using workaround for #1416 and #1315 by setting torchchat device explicitly"
           TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs gguf
 
           echo "::group::Completion"
@@ -137,6 +140,7 @@ jobs:
           sysctl machdep.cpu.core_count
           echo "::endgroup::"
 
+          echo "using workaround for #1416 and #1315 by setting torchchat device explicitly"
           TORCHCHAT_DEVICE=cpu .ci/scripts/run-docs advanced
 
           echo "::group::Completion"

From 1709bf9c9f522204b337b21b6b8956c483f551a1 Mon Sep 17 00:00:00 2001
From: Michael Gschwind <61328285+mikekgfb@users.noreply.github.com>
Date: Sat, 28 Dec 2024 23:15:45 -0800
Subject: [PATCH 3/3] Update build_native.sh

Update to C++11 ABI for AOTI, similar to ET
---
 torchchat/utils/scripts/build_native.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/torchchat/utils/scripts/build_native.sh b/torchchat/utils/scripts/build_native.sh
index 3c2c1c846..a935fa74c 100755
--- a/torchchat/utils/scripts/build_native.sh
+++ b/torchchat/utils/scripts/build_native.sh
@@ -93,7 +93,7 @@ popd
 if [[ "$TARGET" == "et" ]]; then
     cmake -S . -B ./cmake-out -DCMAKE_PREFIX_PATH=`python3 -c 'import torch;print(torch.utils.cmake_prefix_path)'` -DLINK_TORCHAO_OPS="${LINK_TORCHAO_OPS}" -DET_USE_ADAPTIVE_THREADS=ON -DCMAKE_CXX_FLAGS="-D_GLIBCXX_USE_CXX11_ABI=1" -G Ninja
 else
-    cmake -S . -B ./cmake-out -DCMAKE_PREFIX_PATH=`python3 -c 'import torch;print(torch.utils.cmake_prefix_path)'` -DLINK_TORCHAO_OPS="${LINK_TORCHAO_OPS}" -DCMAKE_CXX_FLAGS="-D_GLIBCXX_USE_CXX11_ABI=0" -G Ninja
+    cmake -S . -B ./cmake-out -DCMAKE_PREFIX_PATH=`python3 -c 'import torch;print(torch.utils.cmake_prefix_path)'` -DLINK_TORCHAO_OPS="${LINK_TORCHAO_OPS}" -DCMAKE_CXX_FLAGS="-D_GLIBCXX_USE_CXX11_ABI=1" -G Ninja
 fi
 cmake --build ./cmake-out --target "${TARGET}"_run