.pre-commit-config.yaml
AGENTS.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
NOTICE
README.md
pyproject.toml
.github/requirements/ci-cpu.in
.github/requirements/ci-cpu.txt
.github/workflows/ci.yml
.github/workflows/publish_release.yml
LICENSES/Apache-2.0.txt
dist_moe/__init__.py
dist_moe/_activation_buffer.py
dist_moe/_activation_buffer_offsets.py
dist_moe/_activation_buffer_planner_kernel.py
dist_moe/_blockscaled.py
dist_moe/_blockscaled_ops.py
dist_moe/_blockscaled_weight.py
dist_moe/_buffers.py
dist_moe/_context.py
dist_moe/_execution.py
dist_moe/_postprocess.py
dist_moe/_quantization.py
dist_moe/_routing_metadata.py
dist_moe/_triton_ops.py
dist_moe/_vmm.py
dist_moe/api.py
dist_moe/formats.py
dist_moe.egg-info/PKG-INFO
dist_moe.egg-info/SOURCES.txt
dist_moe.egg-info/dependency_links.txt
dist_moe.egg-info/requires.txt
dist_moe.egg-info/top_level.txt
dist_moe/kernels/__init__.py
dist_moe/kernels/_cuda_context.py
dist_moe/kernels/_dsl_compat.py
dist_moe/kernels/_environment.py
dist_moe/kernels/_grouped_gemm_config.py
dist_moe/kernels/_iket_noop.py
dist_moe/kernels/_iket_shim.py
dist_moe/kernels/_jit_cache.py
dist_moe/kernels/_kernel_name_prefix.py
dist_moe/kernels/_quack_compile_utils.py
dist_moe/kernels/_quack_utils.py
dist_moe/kernels/_quant_conversion.py
dist_moe/kernels/_quant_packing.py
dist_moe/kernels/_swiglu_quant.py
dist_moe/kernels/_tensor_views.py
dist_moe/kernels/activation_buffer.py
dist_moe/kernels/activation_buffer_kernel.py
dist_moe/kernels/blockscaled_config.py
dist_moe/kernels/blockscaled_gemm_tiles.py
dist_moe/kernels/blockscaled_grouped_gemm.py
dist_moe/kernels/blockscaled_grouped_gemm_kernel.py
dist_moe/kernels/blockscaled_quantization_common.py
dist_moe/kernels/blockscaled_quantize.py
dist_moe/kernels/chunked_mega_blockscaled_grouped_gemm.py
dist_moe/kernels/chunked_mega_blockscaled_grouped_gemm_kernel.py
dist_moe/kernels/combine_swiglu_quant.py
dist_moe/kernels/config.py
dist_moe/kernels/dispatch_quant.py
dist_moe/kernels/dist_blockscaled_grouped_gemm.py
dist_moe/kernels/dist_blockscaled_grouped_gemm_kernel.py
dist_moe/kernels/dist_grouped_gemm.py
dist_moe/kernels/dist_grouped_gemm_kernel.py
dist_moe/kernels/gemm_warp_roles.py
dist_moe/kernels/grouped_gemm.py
dist_moe/kernels/grouped_gemm_kernel.py
dist_moe/kernels/mega_blockscaled_grouped_gemm.py
dist_moe/kernels/mega_blockscaled_grouped_gemm_kernel.py
dist_moe/kernels/params.py
dist_moe/kernels/sm103_blockscaled_helpers.py
dist_moe/kernels/swiglu_epilogue.py
dist_moe/kernels/tile_scheduler.py
dist_moe/kernels/weight_borrow.py
dist_moe/kernels/_quack/__init__.py
dist_moe/kernels/_quack/copy_utils.py
dist_moe/kernels/_quack/cute_dsl_utils.py
dist_moe/kernels/_quack/cute_tensor.py
dist_moe/kernels/_quack/layout_utils.py
dist_moe/kernels/_quack/pipeline.py
dist_moe/kernels/_quack/reduce.py
dist_moe/kernels/_quack/reduction_base.py
dist_moe/kernels/_quack/rmsnorm_config.py
dist_moe/kernels/norm/__init__.py
dist_moe/kernels/norm/_fused_dw_reduce_and_quant_kernel.py
dist_moe/kernels/norm/_fused_rmsnorm_combine_kernel.py
dist_moe/kernels/norm/_rmsnorm_bwd_kernel.py
dist_moe/kernels/norm/_rmsnorm_common.py
dist_moe/kernels/norm/_rmsnorm_fwd_kernel.py
dist_moe/kernels/norm/_rmsnorm_small_d_bwd_kernel.py
dist_moe/kernels/norm/_rmsnorm_small_d_fwd_kernel.py
dist_moe/kernels/norm/fused_rmsnorm_combine.py
dist_moe/kernels/norm/rmsnorm.py
dist_moe/kernels/triton/__init__.py
dist_moe/kernels/triton/_thread_id.py
dist_moe/kernels/triton/annotations.py
dist_moe/kernels/triton/barrier.py
dist_moe/kernels/triton/broadcast_n_reduction.py
dist_moe/kernels/triton/comm_utils.py
dist_moe/kernels/triton/conditional_copy.py
dist_moe/kernels/triton/device_trap.py
dist_moe/kernels/triton/dist_dispatch_routing_kernel.py
dist_moe/kernels/triton/fp_math.py
dist_moe/kernels/triton/repr_utils.py
dist_moe/kernels/triton/swiglu.py
dist_moe/kernels/triton_quantization/__init__.py
dist_moe/kernels/triton_quantization/blockscaled_quantize.py
dist_moe/kernels/triton_quantization/env.py
dist_moe/kernels/triton_quantization/formats.py
dist_moe/kernels/triton_quantization/fp_math.py
dist_moe/kernels/triton_quantization/global_scale.py
dist_moe/kernels/triton_quantization/repr_utils.py
dist_moe/kernels/triton_quantization/tma_utils.py
docs/bf16_execution.md
docs/bf16_kernel_design.md
docs/memory_planner.md
docs/mxfp8_execution.md
docs/mxfp8_kernel_design.md
docs/nvfp4_execution.md
docs/nvfp4_kernel_design.md
docs/pipeline_activation_slots.md
docs/postprocess.md
docs/vmm.md
docs/wgrad_accumulation.md
examples/_common.py
examples/bf16_training.py
examples/block_scaled_inference.py
examples/memory_planning.py
examples/mxfp8_training.py
tests/AGENTS.md
tests/test_dist_moe.py
tests/test_dist_moe_vmm.py
tests/test_examples.py
tests/test_package_boundary.py
tests/test_routing_shape_contract.py