metaltile-std-0.1.0

docs.rs

Rust

metaltile-std 0.1.0

MetalTile kernel standard library — benchmark metadata and type definitions

Crate
Source
Builds
Feature flags

..
common
snapshots
affine_int2_gpu_correctness.rs
affine_int356_quantize_gpu_correctness.rs
arange_gpu_correctness.rs
arg_reduce_gpu_correctness.rs
argmax_gpu_correctness.rs
audio_conv1d_gpu_correctness.rs
aura_dequant_rotated_gpu_correctness.rs
aura_encode_gpu_correctness.rs
aura_flash_gpu_correctness.rs
aura_flash_p1_causal_gpu_correctness.rs
aura_flash_sdpa_gpu_correctness.rs
aura_msl_snapshots.rs
aura_score_gpu_correctness.rs
aura_value_gpu_correctness.rs
batched_qkv_qgemv_gpu_correctness.rs
binary_gpu_correctness.rs
binary_two_gpu_correctness.rs
cast_to_f32_gpu_correctness.rs
conv1d_causal_step_gpu_correctness.rs
conv2d_gpu_correctness.rs
conv2d_mma_gpu_correctness.rs
conv3d_gpu_correctness.rs
conv3d_mma_gpu_correctness.rs
copy_gpu_correctness.rs
dequant_gather_gpu_correctness.rs
dequant_gemv_gpu_correctness.rs
fft_bluestein_gpu_correctness.rs
fft_gpu_correctness.rs
flash_quantized_sdpa_gpu_correctness.rs
flash_quantized_sdpa_mask_gpu_correctness.rs
fp_quantized_fp4_gpu_correctness.rs
fp_quantized_fp8_gpu_correctness.rs
fp_quantized_mma_gpu_correctness.rs
fp_quantized_nax_gpu_correctness.rs
fused_gate_activation_gpu_correctness.rs
gated_delta_gpu_correctness.rs
gated_delta_prep_chunk_correctness.rs
gated_delta_prep_step_correctness.rs
gated_delta_replay_gpu_correctness.rs
gated_delta_wy_cpu_oracle.rs
gated_delta_wy_gpu_correctness.rs
gated_delta_wy_microbench.rs
gated_mixer_norm_gpu_correctness.rs
gated_rmsnorm_gpu_correctness.rs
gather_axis_gpu_correctness.rs
gather_gpu_correctness.rs
gemm_gpu_correctness.rs
gemv_gpu_correctness.rs
gemv_masked_gpu_correctness.rs
hadamard_gpu_correctness.rs
hadamard_m_gpu_correctness.rs
indexing_gpu_correctness.rs
kernel_registry_consistency.rs
kv_cache_fp8_gpu_correctness.rs
kv_cache_quant_roundtrip_gpu.rs
kv_cache_update_gpu_correctness.rs
layer_norm_gpu_correctness.rs
logits_min_p_mask_gpu_correctness.rs
logits_processors_gpu_correctness.rs
logits_top_p_mask_gpu_correctness.rs
logits_topk_mask_gpu_correctness.rs
logsumexp_gpu_correctness.rs
mel_spectrogram_gpu_correctness.rs
mma_layout_probe.rs
moe_gather_qmm_gpu_correctness.rs
moe_gather_qmm_int4_m16_m32_correctness.rs
moe_gather_qmm_microbench.rs
moe_gather_qmm_mma_bitwidth_correctness.rs
moe_gather_qmm_mma_int8_gpu_correctness.rs
moe_gather_qmm_mpp_bm64_correctness.rs
moe_gather_qmm_mpp_bm64_int8_correctness.rs
moe_gather_qmm_mpp_bm8_correctness.rs
moe_gather_qmm_mpp_bm8_int8_correctness.rs
moe_gather_qmm_mpp_correctness.rs
moe_gather_qmm_mpp_int8_correctness.rs
moe_gpu_correctness.rs
mpp_matmul_smoke.rs
mt_arg_reduce_gpu_correctness.rs
mt_qmv_gpu_correctness.rs
mt_remainder_gpu_correctness.rs
mt_strided_copy_gpu_correctness.rs
patch_embed_gpu_correctness.rs
patch_embed_mma_gpu_correctness.rs
qmm_gpu_correctness.rs
qmm_int8_fast_gpu_correctness.rs
qmm_mma_b356_gpu_correctness.rs
qmm_mma_dynamic_m_correctness.rs
qmm_mma_int8_gpu_correctness.rs
qmm_mpp_correctness.rs
qmm_mpp_int8_correctness.rs
qmv_int8_fast_gpu_correctness.rs
quantized_family_gpu_correctness.rs
quantized_nax_gpu_correctness.rs
quantized_nax_int8_gpu_correctness.rs
qvm_int4_fast_gpu_correctness.rs
random_gpu_correctness.rs
reduce_col_seg_gpu_correctness.rs
rms_norm_gpu_correctness.rs
rms_norm_per_head_gpu.rs
rms_norm_qgemv_gpu_correctness.rs
rms_norm_qgemv_int8_fast_gpu_correctness.rs
rms_norm_residual_gpu_correctness.rs
rms_norm_rope_gpu_correctness.rs
rms_norm_wide_gpu_correctness.rs
rope_2d_gpu_correctness.rs
rope_gpu_correctness.rs
rope_llama_gpu_correctness.rs
rope_yarn_gpu_correctness.rs
scan_exclusive_gpu_correctness.rs
scan_multi_op_gpu_correctness.rs
scatter_axis_gpu_correctness.rs
sdpa_bidirectional_gpu_correctness.rs
sdpa_decode_2pass_gpu.rs
sdpa_decode_batched_gpu_correctness.rs
sdpa_decode_batched_prefill_gpu_correctness.rs
sdpa_decode_batched_q8_gpu_correctness.rs
sdpa_decode_d256_gpu_correctness.rs
sdpa_decode_d512_gpu_correctness.rs
sdpa_decode_d64_gpu_correctness.rs
sdpa_decode_gpu_correctness.rs
sdpa_decode_swa_gpu.rs
sdpa_multi_gpu_correctness.rs
sdpa_prefill_mma_bf16_gpu.rs
sdpa_prefill_mma_long_t.rs
sdpa_vector_gpu_correctness.rs
sgload_smoke_gpu.rs
sigmoid_scalar_fma_gpu_correctness.rs
softmax_categorical_sample_gpu_correctness.rs
softmax_categorical_sample_matrix.rs
softmax_categorical_sample_perf.rs
softmax_gpu_correctness.rs
sort_gpu_correctness.rs
sort_segmented_gpu_correctness.rs
ssm_gpu_correctness.rs
ssm_replay_gpu_correctness.rs
ssm_step_a2d_gpu_correctness.rs
ssm_step_gpu_correctness.rs
steel_attention_gpu_correctness.rs
steel_attention_nax_gpu_correctness.rs
steel_gemm_fused_nax_gpu_correctness.rs
steel_gemm_gather_gpu_correctness.rs
steel_gemm_gather_nax_gpu_correctness.rs
steel_gemm_gpu_correctness.rs
steel_gemm_masked_gpu_correctness.rs
steel_gemm_segmented_gpu_correctness.rs
steel_gemm_splitk_gpu_correctness.rs
steel_gemm_splitk_nax_gpu_correctness.rs
steel_msl_snapshots.rs
swiglu_gpu_correctness.rs
ternary_gpu_correctness.rs
unary_gpu_correctness.rs
vector_add_gpu_correctness.rs
vocoder_gpu_correctness.rs
winograd_conv_gpu_correctness.rs