[wip] mx: expose a fast path for casting to fp4x2

[vkuzo]

Summary:

not ready for review yet

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:

[vkuzo]

Stack from ghstack (oldest at bottom):

• -> [wip] mx: expose a fast path for casting to fp4x2 #2832

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2832

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 5 New Failures, 1 Unrelated Failure

As of commit a0f764c with merge base d37dcb7 ():

NEW FAILURES - The following jobs have failed:

• Run 1xH100 Tests / test (H100, linux.aws.h100, --pre torch torchvision torchaudio fbgemm-gpu-genai --index-url https... / linux-job (gh)
  RuntimeError: Command docker exec -t 64ac0ba5f3e7c981e9db08deb13b220138e241228bef72219ef45c48b65bc00d /exec failed with exit code 134
• Run Regression Tests / test (CPU 2.8, linux.4xlarge, torch==2.8.0 --index-url https://download.pytorch.org/whl/cpu, cpu) / linux-job (gh)
  RuntimeError: Command docker exec -t 0b01e9e0481831fd2c1c5dd597f468ebd6feda1639a7a657d54363c801bf4f6d /exec failed with exit code 1
• Run Regression Tests / test (CUDA 2.8, linux.g5.12xlarge.nvidia.gpu, torch==2.8.0, cuda, 12.6) / linux-job (gh)
  RuntimeError: Command docker exec -t 66dd718f1c15da02aafc23332512abc4e1df9fd5d068ecee552c987f9bf21d08 /exec failed with exit code 1
• Run Regression Tests / test-nightly (CPU Nightly, linux.4xlarge, --pre torch --index-url https://download.pytorch.org/wh... / linux-job (gh)
  RuntimeError: Command docker exec -t ef7efe9cceec2a152d662365e7bdc28e4c0404ffcb663a3085ab011a9a1a5d81 /exec failed with exit code 1
• Run Regression Tests / test-nightly (CUDA Nightly, linux.g5.12xlarge.nvidia.gpu, --pre torch --index-url https://downloa... / linux-job (gh)
  RuntimeError: Command docker exec -t 228d65d0360ff152fbdc8c2ba10b8b0d9fe030fb7ead4df9ad4a75ba032c4ab4 /exec failed with exit code 1

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• Run TorchAO Experimental Tests / test-cpu-ops (linux.arm64.2xlarge) (gh) (trunk failure)
  /home/ec2-user/actions-runner/_work/ao/ao/torchao/experimental/../../torchao/experimental/ops/embedding_lut/op_embedding_groupwise_lowbit_lut-impl.h:227:50: error: ‘packed_embedding_size’ is not a member of ‘torchao::kernels::cpu::aarch64::embedding’

This comment was automatically generated by Dr. CI and updates every 15 minutes.