vanshbhatia-amdandVansh Bhatia d591d1d511 [Bugfix] Add Kimi K3 MoE support to benchmark_moe.py (#50082) ...

Signed-off-by: Vansh Bhatia <210711135+vanshbhatia-amd@users.noreply.github.com>
Co-authored-by: Vansh Bhatia <210711135+vanshbhatia-amd@users.noreply.github.com>

2026-08-19 19:42:30 +00:00

..

cpu

[Hardware][Power] Add FAST_EXP for Power (#49571)

2026-07-27 05:47:29 +00:00

deepgemm

…

ir

…

__init__.py

…

bench_concat_mla_q.py

…

bench_cp_gather_fp8.py

[Bugfix] Sparse MLA: enable fp8_ds_mla dense prefill (#48642)

2026-07-16 22:44:04 +00:00

benchmark_2d_silu_mul_fp8_quant.py

…

benchmark_activation.py

…

benchmark_block_fp8_gemm.py

…

benchmark_cp_gather.py

[Kernel] Optimize long-context MLA cache gathers (#51739)

2026-08-10 22:23:43 -07:00

benchmark_cutlass_moe_fp8.py

…

benchmark_cutlass_moe_nvfp4.py

…

benchmark_device_communicators.py

…

benchmark_flydsl_moe_w4a16.py

[CI/Build][BugFix][The Rock] Fix get_ssm_device_name to return sanitized, usable filename (#47781)

2026-07-08 12:12:54 +00:00

benchmark_fp8_gemm.py

…

benchmark_fused_collective.py

…

benchmark_fused_moe_lora_one_shot.py

…

benchmark_fused_q_cutedsl.py

[Kernel][SM100] Add a CuTeDSL fused query kernel (#49792)

2026-08-04 15:23:06 -07:00

benchmark_fused_topk.py

…

benchmark_grouped_gemm_cutlass.py

…

benchmark_inkling_qkvr_prep.py

[ROCm] [Model] Enable TML inkling (#48841)

2026-07-27 10:05:46 +00:00

benchmark_int8_gemm.py

…

benchmark_k3_cutedsl_residual.py

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

2026-07-29 14:10:58 +08:00

benchmark_kimi_k3_gemm_rs.py

[Kimi-K3] Add GEMM-RS for sequence parallelism (#52079)

2026-08-13 09:02:28 -07:00

benchmark_kimi_k3_kda_decode.py

[ROCm][Perf] Kimi-K3 Fused kernel for KDA decode (#50654)

2026-08-11 20:39:34 -07:00

benchmark_kimi_k3_latent_moe_tail.py

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

2026-07-29 14:10:58 +08:00

benchmark_kimi_k3_sp_collectives.py

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

2026-07-29 14:10:58 +08:00

benchmark_layernorm.py

…

benchmark_lora.py

…

benchmark_machete.py

…

benchmark_marlin.py

…

benchmark_mla_k_concat.py

…

benchmark_moe_align_block_size.py

…

benchmark_moe_defaults.py

…

benchmark_moe_permute_unpermute.py

…

benchmark_moe.py

[Bugfix] Add Kimi K3 MoE support to benchmark_moe.py (#50082)

2026-08-19 19:42:30 +00:00

benchmark_mrope.py

…

benchmark_mxfp4_qutlass.py

…

benchmark_nvfp4_gemm.py

…

benchmark_nvfp4_quant.py

…

benchmark_nvfp4_qutlass.py

…

benchmark_paged_attention.py

…

benchmark_per_token_group_quant.py

…

benchmark_per_token_quant_fp8.py

…

benchmark_quant.py

…

benchmark_rdna_hybrid_w4a16_gemm.py

[ROCm][Kernel] Add HybridW4A16LinearKernel: Triton prefill + HIP skinny decode (#40977)

2026-07-13 20:22:00 -07:00

benchmark_relu_squared.py

[Kernel] Implement CUDA kernel for ReLUSquaredActivation (relu^2) (#39058)

2026-07-12 19:18:03 -07:00

benchmark_reshape_and_cache_flash.py

…

benchmark_reshape_and_cache.py

…

benchmark_rmsnorm.py

…

benchmark_rope.py

…

benchmark_router_gemm.py

…

benchmark_selective_state_update.py

[XPU] Add tuned Mamba SSU configs for Intel Arc Pro B70 (#50534)

2026-08-13 12:36:55 +00:00

benchmark_shapes.py

…

benchmark_silu_mul_fp8_quant.py

…

benchmark_thinking_budget.py

[Feat] Support thinking_token_budget in Model Runner V2 (#46727)

2026-08-07 03:36:18 +00:00

benchmark_trtllm_decode_attention.py

…

benchmark_trtllm_prefill_attention.py

…

benchmark_vit_aiter_fp8_attn.py

[ROCm] Add AITER FP8 ViT encoder attention (#49937)

2026-07-30 06:22:10 +00:00

benchmark_vit_bilinear_pos_embed.py

…

benchmark_vit_fp8_attn.py

…

benchmark_w8a8_block_fp8.py

[CI/Build][BugFix][The Rock] Fix get_ssm_device_name to return sanitized, usable filename (#47781)

2026-07-08 12:12:54 +00:00

graph_machete_bench.py

…

requirements.txt

…

utils.py

…

weight_shapes.py

…