[executorch][muse] Export packed DFlash drafts for CUDA batching

b2621c8

Select commit

Loading

Failed to load commit list.

Uh oh!

There was an error while loading. Please reload this page.

Meta CLA

Meta CLA Check

Meta CodeSync

Meta Import Checks

Meta Internal-Only Changes Check

Labeler on: pull_request_target 3

label

Lint on: pull_request 11

Get changed files / get-changed-files

link-check / lint-urls

link-check / lint-xrefs

link-check / lint-file-size

lintrunner-mypy

lintrunner

periodic on: pull_request 16

Resolve CI docker image / resolve

gather-models

test-models-linux (buck2, mv3, portable, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (buck2, mv3, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (cmake, mv3, portable, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (cmake, mv3, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (cmake, vit, portable, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (cmake, vit, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job

Test CUDA Builds on: pull_request 72

Get changed files / get-changed-files

CI run decision / decide

Validate benchmark dispatch inputs

test-executorch-cuda-build-12.6 / linux-job

test-executorch-cuda-build-13.0 / linux-job

test-executorch-cuda-build-13.4 / linux-job

test-models-cuda / linux-job

export-cuda-multi-arch-a100 / linux-job

unittest-cuda / linux-job

unittest-cuda-muse-glimmer-batching / linux-job

unittest-cuda-quantized-gemm (int4) / linux-job

unittest-cuda-quantized-gemm (large-int5-int6-int8-graph-timing) / linux-job

unittest-cuda-runtime / linux-job

test-muse-glimmer-cuda-e2e-kquant-17gb-solo-text / linux-job

test-muse-glimmer-cuda-e2e-kquant-17gb-solo-text-batching / linux-job

test-muse-glimmer-cuda-e2e-kquant-17gb-dflash-image / linux-job

test-muse-glimmer-cuda-e2e-kquant-dynamic-solo-text / linux-job

test-muse-glimmer-cuda-e2e-kquant-dynamic-dflash-image / linux-job

test-model-cuda-e2e-Voxtral-Mini-3B-2507-non-quantized / linux-job

test-model-cuda-e2e-Voxtral-Mini-3B-2507-quantized-int4-tile-packed / linux-job

test-model-cuda-e2e-Voxtral-Mini-3B-2507-quantized-int4-weight-only / linux-job

test-model-cuda-e2e-Voxtral-Mini-4B-Realtime-2602-quantized-int4-tile-packed / linux-job

test-model-cuda-e2e-diar_streaming_sortformer_4spk-v2-non-quantized / linux-job

test-model-cuda-e2e-whisper-small-non-quantized / linux-job

test-model-cuda-e2e-whisper-medium-non-quantized / linux-job

test-model-cuda-e2e-whisper-large-v3-turbo-quantized-int4-tile-packed / linux-job

test-model-cuda-e2e-whisper-large-v3-turbo-quantized-int4-weight-only / linux-job

test-model-cuda-e2e-gemma-3-4b-it-non-quantized / linux-job

test-model-cuda-e2e-gemma-3-4b-it-quantized-int4-tile-packed / linux-job

test-model-cuda-e2e-Qwen3-0.6B-non-quantized / linux-job

test-model-cuda-e2e-Qwen3-0.6B-quantized-int4-tile-packed / linux-job

test-model-cuda-e2e-parakeet-tdt-non-quantized / linux-job

test-model-cuda-e2e-parakeet-tdt-quantized-int4-tile-packed / linux-job

test-model-cuda-e2e-dinov2-small-imagenet1k-1-layer-non-quantized / linux-job

test-model-cuda-e2e-Qwen3.5-35B-A3B-HQQ-INT4-quantized-int4-tile-packed / linux-job

test-model-cuda-e2e-gemma-4-31B-it-GGUF-quantized-int4-tile-packed / linux-job

check-all-cuda-builds

merge-and-test-cuda-multi-arch-a10g / linux-job

upload-benchmark-results

test-cuda-merged-pte-a100 / linux-job

Cadence Build & Test on: pull_request 24

Resolve CI docker image

cpu-build / build

hifi-build / hifi4

vision-build / vision

hifi1s-build / hifi1s

hifi5s-build / hifi5s

cpu-test / test-aot / test-aot

cpu-test / test-ops / test-ops

hifi-op-test / hifi4

hifi1s-op-test / hifi1s

hifi5s-op-test / hifi5s

Build Presets on: pull_request 30

Resolve CI docker image / resolve

apple (macos) / build

apple (ios) / build

apple (ios-simulator) / build

apple (pybind) / build

apple (profiling) / build

apple (llm) / build

windows (pybind) / build

windows (windows) / build

zephyr (zephyr) / build

linux (linux, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-clang12) / build

linux (linux, mt-l-arm64g4-16-62, executorch-ubuntu-22.04-gcc11-aarch64) / build

linux (pybind, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-clang12) / build

linux (pybind, mt-l-arm64g4-16-62, executorch-ubuntu-22.04-gcc11-aarch64) / build

linux (llm, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-clang12) / build

linux (llm, mt-l-arm64g4-16-62, executorch-ubuntu-22.04-gcc11-aarch64) / build

Test QNN Backend on: pull_request 6

test-qnn / Resolve CI docker image / resolve

test-qnn / test-backend-macos

test-qnn / test-backend-linux (qnn, models) / linux-job

test-qnn / test-backend-linux (qnn, operators) / linux-job

test-qnn / package-golden-artifacts

MLX on: pull_request 62

CI run decision / decide

test-mlx / test-mlx

test-mlx-supertonic / test-mlx-supertonic

test-mlx-qwen35-moe / test-mlx-qwen35-moe

test-mlx-muse-glimmer-build / test-mlx-muse-glimmer-build

test-mlx-nemotron3-diarization-build / test-mlx-nemotron3-diarization-build

backend-tester (models) / test-mlx-backend-models

backend-tester (operators) / test-mlx-backend-operators

test-mlx-parakeet / test-mlx-parakeet

test-mlx-voxtral / test-mlx-voxtral

test-mlx-voxtral-realtime / test-mlx-voxtral-realtime

test-mlx-whisper / test-mlx-whisper

test-mlx-stories110m / test-mlx-stories110m

test-mlx-llm (unsloth/Llama-3.2-1B-Instruct, llama-1b, false, 4w, macos-14-xlarge) / test-mlx-llm-llama-1b-4w

test-mlx-llm (unsloth/Llama-3.2-1B-Instruct, llama-1b, false, nvfp4, macos-14-xlarge) / test-mlx-llm-llama-1b-nvfp4

test-mlx-llm (unsloth/Llama-3.2-1B-Instruct, llama-1b, true, 4w, macos-14-xlarge) / test-mlx-llm-llama-1b-custom-4w

test-mlx-llm (unsloth/Llama-3.2-1B-Instruct, llama-1b, true, nvfp4, macos-14-xlarge) / test-mlx-llm-llama-1b-custom-nvfp4

test-mlx-llm (unsloth/Qwen3-0.6B, qwen3-0.6b, false, 4w, macos-14-xlarge) / test-mlx-llm-qwen3-0.6b-4w

test-mlx-llm (unsloth/Qwen3-0.6B, qwen3-0.6b, false, nvfp4, macos-14-xlarge) / test-mlx-llm-qwen3-0.6b-nvfp4

test-mlx-llm (unsloth/Qwen3-0.6B, qwen3-0.6b, true, 4w, macos-14-xlarge) / test-mlx-llm-qwen3-0.6b-custom-4w

test-mlx-llm (unsloth/Qwen3-0.6B, qwen3-0.6b, true, nvfp4, macos-14-xlarge) / test-mlx-llm-qwen3-0.6b-custom-nvfp4

test-mlx-llm (unsloth/gemma-3-1b-it, gemma3-1b, false, 4w, macos-14-xlarge) / test-mlx-llm-gemma3-1b-4w

test-mlx-llm (unsloth/gemma-3-1b-it, gemma3-1b, false, nvfp4, macos-14-xlarge) / test-mlx-llm-gemma3-1b-nvfp4

test-mlx-llm (unsloth/gemma-3-1b-it, gemma3-1b, true, 4w, macos-14-xlarge) / test-mlx-llm-gemma3-1b-custom-4w

test-mlx-llm (unsloth/gemma-3-1b-it, gemma3-1b, true, nvfp4, macos-14-xlarge) / test-mlx-llm-gemma3-1b-custom-nvfp4

test-mlx-llm (google/gemma-4-E2B-it, gemma4-e2b, true, 4w, macos-15-xlarge) / test-mlx-llm-gemma4-e2b-custom-4w

test-mlx-llm (google/gemma-4-E2B-it, gemma4-e2b, false, 4w, macos-15-xlarge) / test-mlx-llm-gemma4-e2b-4w

test-mlx-dflash / test-mlx-dflash

test-mlx-llm-offgraph (unsloth/Llama-3.2-1B-Instruct, llama-1b, llama3, macos-14-xlarge) / test-mlx-llm-offgraph-llama-1b

test-mlx-llm-offgraph (unsloth/gemma-3-1b-it, gemma3-1b, gemma, macos-14-xlarge) / test-mlx-llm-offgraph-gemma3-1b

test-mlx-llm-offgraph (google/gemma-4-E2B-it, gemma4-e2b, gemma4, macos-15-xlarge) / test-mlx-llm-offgraph-gemma4-e2b

Build documentation on: pull_request 4

Resolve CI docker image / resolve

build (buck2) / Build doc

upload-gh-pages

Test WebGPU Backend on: pull_request 6

test-webgpu / Resolve CI docker image / resolve

test-webgpu / test-backend-macos

test-webgpu / test-backend-linux (webgpu, models) / linux-job

test-webgpu / test-backend-linux (webgpu, operators) / linux-job

test-webgpu / package-golden-artifacts

Build Linux Wheels on: pull_request 4

generate-matrix / generate

pytorch/executorch / build-manywheel-py3_11-cpu

pytorch/executorch / upload / upload-manywheel-py3_11-cpu

Test Cortex-M Backend on: pull_request 1

Get changed files / get-changed-files

test-cortex-m

Test QNN Windows MSVC build on: pull_request 2

build-qnn-windows-x64 / windows-job

build-qnn-windows-arm64

Test NXP Backend on: pull_request 1

Get changed files / get-changed-files

test-nxp

Test CoreML Backend on: pull_request 1

Get changed files / get-changed-files

test-coreml

Build Aarch64 Linux Wheels on: pull_request 4

generate-matrix / generate

pytorch/executorch / build-wheel-py3_11-cpu-aarch64

pytorch/executorch / upload / upload-wheel-py3_11-cpu-aarch64

Test XNNPACK Backend on: pull_request 6

test-xnnpack / Resolve CI docker image / resolve

test-xnnpack / test-backend-macos

test-xnnpack / test-backend-linux (xnnpack, models) / linux-job

test-xnnpack / test-backend-linux (xnnpack, operators) / linux-job

test-xnnpack / package-golden-artifacts

Test Vulkan Backend on: pull_request 6

test-vulkan / Resolve CI docker image / resolve

test-vulkan / test-backend-macos

test-vulkan / test-backend-linux (vulkan, models) / linux-job

test-vulkan / test-backend-linux (vulkan, operators) / linux-job

test-vulkan / package-golden-artifacts

Test ARM Backend on: pull_request 12

test-arm / Resolve CI docker image / resolve

test-arm / test-backend-macos

test-arm / test-backend-linux (arm_tosa_fp, models) / linux-job

test-arm / test-backend-linux (arm_tosa_fp, operators) / linux-job

test-arm / package-golden-artifacts

test-arm-vgf / Resolve CI docker image / resolve

test-arm-vgf / test-backend-macos

test-arm-vgf / test-backend-linux (arm_vgf_fp, models) / linux-job

test-arm-vgf / test-backend-linux (arm_vgf_fp, operators) / linux-job

test-arm-vgf / package-golden-artifacts

Build Aarch64 Linux CUDA Wheels on: pull_request 6

generate-matrix / generate

filter-matrix

pytorch/executorch / build-wheel-py3_11-cuda-aarch6413_2-aarch64

pytorch/executorch / upload / upload-wheel-py3_11-cuda-aarch6413_2-aarch64

pull on: pull_request 230

Resolve CI docker image / resolve

Get changed files / get-changed-files

CI run decision / decide

android / build-android

android / run-emulator

unittest / Resolve CI docker image / resolve

unittest / macos / macos-job

unittest / windows / windows-job

unittest / linux / linux-job

unittest-editable / Resolve CI docker image / resolve

unittest-editable / macos / macos-job

unittest-editable / windows / windows-job

unittest-editable / linux / linux-job

unittest-buck / Resolve CI docker image / resolve

unittest-buck / macos / macos-job

unittest-buck / windows

unittest-buck / linux / linux-job

test-qnn-testsuite-linux / Resolve CI docker image / resolve

test-qnn-testsuite-linux / test-backend-macos

test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job

test-qnn-testsuite-linux / test-backend-linux (qnn, operators) / linux-job

test-qnn-testsuite-linux / package-golden-artifacts

test-qnn-wheel-packages-linux (3.11) / linux-job

test-qnn-wheel-packages-linux (3.12) / linux-job

test-qnn-wheel-packages-linux (3.13) / linux-job

test-setup-linux-gcc / linux-job

test-models-linux-basic (mv3, portable, cmake, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-clan... / linux-job

test-models-linux-basic (mv3, portable, cmake, mt-l-arm64g4-16-62, executorch-ubuntu-22.04-gcc11-... / linux-job

test-models-linux-basic (mv3, portable, buck2, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-clan... / linux-job

test-models-linux-basic (mv3, xnnpack-quantization-delegation, cmake, mt-l-x86iavx512-8-64, execu... / linux-job

test-models-linux-basic (mv3, xnnpack-quantization-delegation, cmake, mt-l-arm64g4-16-62, executo... / linux-job

test-models-linux-basic (mv3, xnnpack-quantization-delegation, buck2, mt-l-x86iavx512-8-64, execu... / linux-job

test-models-linux-basic (vit, portable, cmake, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-clan... / linux-job

test-models-linux-basic (vit, portable, cmake, mt-l-arm64g4-16-62, executorch-ubuntu-22.04-gcc11-... / linux-job

test-models-linux-basic (vit, portable, buck2, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-clan... / linux-job

test-models-linux-basic (vit, xnnpack-quantization-delegation, cmake, mt-l-x86iavx512-8-64, execu... / linux-job

test-models-linux-basic (vit, xnnpack-quantization-delegation, cmake, mt-l-arm64g4-16-62, executo... / linux-job

test-models-linux-basic (vit, xnnpack-quantization-delegation, buck2, mt-l-x86iavx512-8-64, execu... / linux-job

test-models-linux (linear, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (linear, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (add, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (add, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (add_mul, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (add_mul, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (ic3, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (ic3, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (mv2, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (mv2, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (resnet18, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (resnet18, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (resnet50, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (resnet50, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (mobilebert, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (mobilebert, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (emformer_transcribe, portable, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (emformer_transcribe, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64) / linux-job

test-models-linux (ic4, portable, mt-l-x86iavx512-16-128) / linux-job

test-models-linux (ic4, xnnpack-quantization-delegation, mt-l-x86iavx512-16-128) / linux-job

test-models-linux (emformer_join, portable, mt-l-x86iavx512-16-128) / linux-job

test-models-linux (emformer_join, xnnpack-quantization-delegation, mt-l-x86iavx512-16-128) / linux-job

test-models-linux (phi_4_mini, portable, mt-l-x86iavx512-16-128) / linux-job

test-models-linux (llama3_2_vision_encoder, portable, mt-l-x86iavx512-16-128) / linux-job

test-models-linux (w2l, portable, mt-l-x86iavx512-16-128) / linux-job

test-parakeet-xnnpack-linux / linux-job

test-voxtral-realtime-xnnpack-linux / linux-job

test-llama-runner-linux (fp32, xnnpack+custom+qe, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-c... / linux-job

test-llama-runner-linux (fp32, xnnpack+custom+qe, mt-l-arm64g4-16-62, executorch-ubuntu-22.04-gcc... / linux-job

test-llama-runner-linux (fp32, xnnpack+custom+quantize_kv, mt-l-x86iavx512-8-64, executorch-ubunt... / linux-job

test-llama-runner-linux (fp32, xnnpack+custom+quantize_kv, mt-l-arm64g4-16-62, executorch-ubuntu-... / linux-job

test-llama-runner-linux (fp32, xnnpack+quantize_kv, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04... / linux-job

test-llama-runner-linux (fp32, xnnpack+quantize_kv, mt-l-arm64g4-16-62, executorch-ubuntu-22.04-g... / linux-job

test-llama-runner-linux (bf16, custom, mt-l-x86iavx512-8-64, executorch-ubuntu-22.04-clang12) / linux-job

test-llama-runner-linux-android / linux-job

test-custom-ops-linux / linux-job

test-selective-build-linux / linux-job

test-multimodal-linux (gemma3-4b) / linux-job

test-moshi-linux / linux-job

test-quantized-aot-lib-linux / linux-job

test-binary-size-linux-gcc / linux-job

test-binary-size-linux / linux-job

test-arm-cortex-m-size-test (bare_metal) / linux-job

test-arm-cortex-m-size-test (zephyr-preset) / linux-job

test-mcu-cortex-m-backend / linux-job

test-qnn-buck-build-linux / linux-job

test-arm-backend-no-driver (test_pytest_ops_no_target) / linux-job

test-arm-backend-no-driver (test_pytest_ops_tosa) / linux-job

test-arm-backend-no-driver (test_pytest_models_tosa) / linux-job

test-arm-backend-no-driver (test_run_tosa) / linux-job

test-arm-backend-vkml (test_pytest_ops_vkml) / linux-job

test-arm-backend-vkml (test_ootb_tests_vgf) / linux-job

test-arm-backend-vkml (test_runtime_vgf) / linux-job

test-arm-backend-public-api-backward-compatibility / linux-job

test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job

test-llama-runner-qnn-linux (fp32, qnn_8a8w, qnn) / linux-job

test-static-llama-qnn-linux (stories_110m) / linux-job

test-static-llama-qnn-linux (stories_260k_bc) / linux-job

test-sqnr-static-llm-qnn-linux (smollm2_135m) / linux-job

test-qnn-models-linux (mv2) / linux-job

test-qnn-models-linux (mv3) / linux-job

test-qnn-models-linux (dl3) / linux-job

test-qnn-direct-build-linux / linux-job

test-qnn-passes-linux / linux-job

test-qnn-delegate-linux / linux-job

test-phi-3-mini-runner-linux / linux-job

test-qnn-python-imports-linux / linux-job

test-eval_llama-wikitext-linux / linux-job

test-llama_runner_eager-linux / linux-job

test-lora-linux / linux-job

test-lora-multimethod-linux / linux-job

test-mediatek-models-linux

test-openvino-linux / linux-job

test-build-wasm-linux / linux-job

unittest-wasm-bindings / linux-job

unittest-wasm-bindings (--enable-etdump) / linux-job

unittest-nxp-neutron / linux-job

test-vulkan-models-linux / linux-job

test-vulkan-operators-linux / linux-job

nxp-build-test / linux-job

nxp-mcuxpresso-test / linux-job

test-arduino-library

test-minimal-wheel-linux

test-pybindings-no-aten

llm-server / Resolve CI docker image / resolve

llm-server / linux / linux-job

test-coreml-bc-macos (${{ matrix.runner }})

Build Windows Wheels on: pull_request 4

generate-matrix / generate

pytorch/executorch / build-wheel-py3_11-cpu

pytorch/executorch / upload / upload-wheel-py3_11-cpu

Build Linux CUDA Wheels on: pull_request 6

generate-matrix / generate

filter-matrix

pytorch/executorch / build-manywheel-py3_11-cuda13_2

pytorch/executorch / upload / upload-manywheel-py3_11-cuda13_2

Build macOS Wheels on: pull_request 7

generate-matrix / generate

pytorch/executorch / build-wheel-py3_11-cpu

pytorch/executorch / upload / upload-wheel-py3_11-cpu

periodic on: pull_request 15

Resolve CI docker image / resolve

gather-models

test-models-linux (buck2, mv3, portable, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (buck2, mv3, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (cmake, mv3, portable, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (cmake, mv3, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (cmake, vit, portable, mt-l-x86iavx512-8-64, 90) / linux-job

test-models-linux (cmake, vit, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job

CodeQL on: dynamic 4

Analyze (actions)

Analyze (c-cpp)

Analyze (javascript-typescript)

Analyze (python)

Code scanning results

CodeQL

Select a check to view from the sidebar