[ROCm][Perf] Any-shape low-latency MoE router GEMM on MI355 (#61895)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Andreas Karatzas
2026-10-15 23:22:31 -05:00
committed by GitHub
co-authored by Claude
parent 642c18d64c
commit b466fbacd2
6 changed files with 296 additions and 75 deletions
+18 -2
View File
@@ -4704,16 +4704,32 @@ steps:
kernels/test_fused_inv_rope_fp8_quant.py
kernels/test_fused_minimax_m3_qknorm_rope_kv_insert.py
kernels/test_fused_quant_activation.py
kernels/test_gate_linear_rocm_dispatch.py
kernels/test_gemm_rs_ar.py
kernels/test_kpool_decode_update_batched.py
kernels/test_minimax_m3_amd_ops.py
kernels/test_minimax_m3_sparse_attn_fp8_scale.py
kernels/test_onednn.py
kernels/test_relu2_fp8_quant.py
kernels/test_rocm_fp32_router_gemm.py
--deselect=tests/kernels/test_bf16_skinny_gemm.py::test_every_dsv3_routed_shape_is_instantiated
- label: ":amd: (MI355) Gate Linear Router Kernels"
timeout_in_minutes: 20
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
dind: false
agent_pool: mi355_1
optional: true
working_dir: "/vllm-workspace/"
source_file_dependencies:
- vllm/model_executor/layers/fused_moe/router/gate_linear.py
- vllm/model_executor/layers/fused_moe/router/rocm_fp32_router_gemm.py
- vllm/model_executor/layers/fused_moe/router/bf16x3_router_gemm_rocm.py
- vllm/platforms/rocm.py
- tests/kernels/test_rocm_fp32_router_gemm.py
- tests/kernels/test_gate_linear_rocm_dispatch.py
- tests/kernels/test_bf16x3_router_gemm_rocm.py
commands:
- pytest -v -s tests/kernels/test_rocm_fp32_router_gemm.py tests/kernels/test_gate_linear_rocm_dispatch.py tests/kernels/test_bf16x3_router_gemm_rocm.py
- label: ":amd: (MI355 DPX) Attention DiffKV Kernels"
timeout_in_minutes: 35
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
+18 -3
View File
@@ -290,7 +290,6 @@ steps:
kernels/test_apply_repetition_penalties.py
kernels/test_awq_int4_to_int8.py
kernels/test_bf16_skinny_gemm.py
kernels/test_bf16x3_router_gemm_rocm.py
kernels/test_cache_kernels.py
kernels/test_compressor_kv_cache.py
kernels/test_cp_gather_fp8.py
@@ -305,14 +304,12 @@ steps:
kernels/test_fused_inv_rope_fp8_quant.py
kernels/test_fused_minimax_m3_qknorm_rope_kv_insert.py
kernels/test_fused_quant_activation.py
kernels/test_gate_linear_rocm_dispatch.py
kernels/test_gemm_rs_ar.py
kernels/test_kpool_decode_update_batched.py
kernels/test_minimax_m3_amd_ops.py
kernels/test_minimax_m3_sparse_attn_fp8_scale.py
kernels/test_onednn.py
kernels/test_relu2_fp8_quant.py
kernels/test_rocm_fp32_router_gemm.py
--deselect=tests/kernels/test_bf16_skinny_gemm.py::test_every_dsv3_routed_shape_is_instantiated
- label: ":nvidia: (L4) Attention Kernels Shard %N"
@@ -725,6 +722,24 @@ steps:
- nvidia-smi
- pytest -v -s tests/kernels/test_ll_bf16_gemm.py
- pytest -v -s tests/kernels/test_ll_fp32w_gemm.py
mirror:
amd:
label: ":amd: (MI355) Gate Linear Router Kernels"
dind: false
device: mi355_1
timeout_in_minutes: 20
depends_on:
- image-build-amd
source_file_dependencies:
- vllm/model_executor/layers/fused_moe/router/gate_linear.py
- vllm/model_executor/layers/fused_moe/router/rocm_fp32_router_gemm.py
- vllm/model_executor/layers/fused_moe/router/bf16x3_router_gemm_rocm.py
- vllm/platforms/rocm.py
- tests/kernels/test_rocm_fp32_router_gemm.py
- tests/kernels/test_gate_linear_rocm_dispatch.py
- tests/kernels/test_bf16x3_router_gemm_rocm.py
commands:
- pytest -v -s tests/kernels/test_rocm_fp32_router_gemm.py tests/kernels/test_gate_linear_rocm_dispatch.py tests/kernels/test_bf16x3_router_gemm_rocm.py
- label: ":nvidia: (DGX) Spark b12x Linear Kernels Nightly"
key: b12x-linear-kernels-dgx-spark-nightly