ferrotorch-gpu-0.6.1

docs.rs

Rust

ferrotorch-gpu 0.6.1

CUDA GPU backend for ferrotorch

Crate
Source
Builds
Feature flags

..
conformance
_probe_b1_ptx_jit.rs
_probe_backward_f64.rs
_probe_broadcast.rs
_probe_cummax_cummin_f64.rs
_probe_logcumsumexp_f64.rs
_probe_pow_f64.rs
_probe_prod_backward.rs
bf16_vit_block_e2e.rs
conformance_gpu_backend.rs
conformance_gpu_blas_family.rs
conformance_gpu_cat.rs
conformance_gpu_kernels.rs
conformance_gpu_lifecycle.rs
conformance_surface_coverage.rs
divergence_add_scaled_fused_reaudit.rs
divergence_add_vec4_correctness_and_ascii_ptx.rs
divergence_airy_zeta_gpu_f32.rs
divergence_airy_zeta_gpu_reaudit.rs
divergence_bessel_i_gpu_boundary_audit.rs
divergence_bf16_req7_embedding_gather_to_f32.rs
divergence_blas_req8_into_consumers.rs
divergence_bool_broadcast_reaudit.rs
divergence_cdist_compute_mode.rs
divergence_entr_ndtr_ndtri_f32_edges.rs
divergence_full_reduction_on_device_pass2.rs
divergence_full_reduction_reaudit.rs
divergence_gelu_backward_tanh_correctness.rs
divergence_masked_fill_reaudit.rs
divergence_masked_fill_storage_offset_gpu.rs
divergence_masked_scatter_forward_reaudit.rs
divergence_matmul_nt_linear_fused_1679.rs
divergence_matmul_nt_reaudit.rs
divergence_modified_bessel_k_gpu_f32.rs
divergence_modified_bessel_k_gpu_reaudit.rs
divergence_on_device_philox_live_audit.rs
divergence_roll_f64_unique_consecutive_gpu.rs
divergence_roll_unique_consecutive_gpu_reaudit.rs
divergence_scatter_add_segments_gpu.rs
divergence_scatter_add_segments_gpu_reaudit.rs
divergence_scatter_gather_gpu.rs
divergence_scatter_gather_gpu_reaudit.rs
divergence_searchsorted_inf_boundnan.rs
divergence_searchsorted_nan.rs
divergence_special_hermite_limit.rs
divergence_special_native_t_reaudit.rs
divergence_special_shifted_native_t.rs
divergence_spherical_bessel_j0_sin_approx.rs
divergence_storage_offset_class_completeness.rs
divergence_storage_offset_gpu_ops_reaudit.rs
divergence_storage_offset_gpu_ops_reaudit_extended.rs
divergence_topk_nan_inf_extra.rs
divergence_topk_nan_ordering.rs
divergence_triangular_batched_autograd.rs
divergence_triangular_batched_kextent.rs
divergence_triangular_batched_nonsquare.rs
divergence_triangular_nonuniform_grad_backward.rs
divergence_unique_consecutive_neu_reaudit.rs
divergence_unique_gpu.rs
divergence_unique_gpu_reaudit.rs
eig_complex_transpose_e2e.rs
eig_divergence_probes_1687.rs
on_device_rng.rs
ptx_compile_guard.rs
regression_logical_len_compare_where_matrix.rs
regression_storage_offset_class_guard.rs
test_gpu_autograd.rs
test_gpu_channels_last.rs
test_gpu_clamp_backward.rs
test_gpu_diag_cdist.rs
test_gpu_eigh.rs
test_gpu_fft.rs
test_gpu_fft2.rs
test_gpu_fill_f64.rs
test_gpu_graph_pool.rs
test_gpu_lstsq.rs
test_gpu_lu_factor.rs
test_gpu_masked.rs
test_gpu_matrix_norm.rs
test_gpu_prod.rs
test_gpu_searchsorted.rs
test_gpu_solve_dev.rs
test_gpu_special_polynomials.rs
test_gpu_stream_priority.rs
test_gpu_strided_copy.rs
test_gpu_strided_scatter.rs
test_gpu_sum_dim_backward.rs
test_gpu_triangular.rs
transpose_complex_kernel.rs