From 34b9784a7df4a6e754fef5cf59b2f37bb3b59cf8 Mon Sep 17 00:00:00 2001 From: leslief Date: Wed, 5 Aug 2026 15:53:58 -0700 Subject: [PATCH 1/2] [https://nvbugs/6564714][fix] Fix the FP8BlockScaleMoERunner get_fallback_tactic Signed-off-by: leslief --- .../custom_ops/trtllm_gen_custom_ops.py | 4 ++-- tests/integration/test_lists/waives.txt | 20 ------------------- 2 files changed, 2 insertions(+), 22 deletions(-) diff --git a/tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py b/tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py index 776e167ab950..42272300c12b 100644 --- a/tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py +++ b/tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py @@ -922,8 +922,8 @@ def get_fallback_tactic(self, hidden_size: int, the profiling cache. The result depends only on the key below, so memoize it the same way ``runner_dict`` memoizes the runner. """ - key = (self.top_k, hidden_size, self.intermediate_size, - self.local_num_experts, num_tokens) + key = (self.top_k, self.num_fused_shared_experts, hidden_size, + self.intermediate_size, self.local_num_experts, num_tokens) tactic = FP8BlockScaleMoERunner.fallback_tactic_dict.get(key) if tactic is None: tactic = tuple( diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 4b25ad10b52d..b150d445b4a6 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -361,7 +361,6 @@ perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_grace_blackwel perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp8_blackwell-r1_fp8_tp8_mtp3_8k1k] SKIP (https://nvbugs/6432948) perf/test_perf_sanity.py::test_e2e[aggr_upload-dynamo_gpt_oss_120b_fp4_blackwell-gpt_oss_fp4_tep4_adp_cutlass_8k1k] SKIP (https://nvbugs/6374910) perf/test_perf_sanity.py::test_e2e[aggr_upload-glm5_fp4_blackwell-glm5_fp4_tep8_mtp3_8k1k] SKIP (https://nvbugs/6329155) -perf/test_perf_sanity.py::test_e2e[aggr_upload-host_perf_deepseek_v3_lite-v3lite_fp8_bs8_128_256] SKIP (https://nvbugs/6564714) perf/test_perf_sanity.py::test_e2e[aggr_upload-k25_thinking_fp4_2_nodes_grace_blackwell-k25_thinking_fp4_tep8_32k8k] SKIP (https://nvbugs/6422339) perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_dep8_8k1k] SKIP (https://nvbugs/6535767) perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_dep8_mtp3_8k1k] SKIP (https://nvbugs/6535767) @@ -441,27 +440,8 @@ unittest/auto_deploy/multigpu/smoke/test_ad_allreduce_strategies.py::test_allred unittest/auto_deploy/multigpu/smoke/test_ad_allreduce_strategies.py::test_allreduce_strategies[ONESHOT] SKIP (https://nvbugs/6517839) unittest/auto_deploy/multigpu/smoke/test_ad_allreduce_strategies.py::test_allreduce_strategies[SYMM_MEM] SKIP (https://nvbugs/6517839) unittest/auto_deploy/multigpu/smoke/test_ad_allreduce_strategies.py::test_allreduce_strategies[TWOSHOT] SKIP (https://nvbugs/6517839) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[256-2-4-256-1] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[256-2-4-256-4] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[256-2-4-512-1] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[256-2-4-512-4] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[256-2-8-256-1] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[256-2-8-256-4] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[256-2-8-512-1] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[256-2-8-512-4] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[512-2-4-256-1] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[512-2-4-256-4] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[512-2-4-512-1] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[512-2-4-512-4] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[512-2-8-256-1] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[512-2-8-256-4] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[512-2-8-512-1] SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py::test_trtllm_finegrained_fp8_moe_blackwell[512-2-8-512-4] SKIP (https://nvbugs/6564714) unittest/auto_deploy/singlegpu/models/test_glm4_moe_modeling.py::test_glm4_moe_decoder_layer_equivalence[1-dtype0-1-8] SKIP (https://nvbugs/6566730) unittest/auto_deploy/singlegpu/models/test_glm4_moe_modeling.py::test_glm4_moe_moe_equivalence[dtype0-1-8] SKIP (https://nvbugs/6566730) -unittest/auto_deploy/singlegpu/transformations/library/test_moe_fusion.py SKIP (https://nvbugs/6564714) -unittest/auto_deploy/singlegpu/transformations/library/test_moe_fusion.py::test_trtllm_quant_finegrained_fp8_moe_fused_correctness SKIP (https://nvbugs/6564714) unittest/bindings/test_transfer_agent_bindings.py::TestMooncakeFunctionalTransfer::test_mooncake_wait_in_progress_on_zero_timeout SKIP (https://nvbugs/6517836) unittest/bindings/test_transfer_agent_bindings.py::TestMooncakeFunctionalTransfer::test_mooncake_write_transfer_gpu_tensor SKIP (https://nvbugs/6517836) unittest/bindings/test_transfer_agent_bindings.py::TestMooncakeFunctionalTransfer::test_mooncake_write_transfer_multiple_chunks SKIP (https://nvbugs/6517836) From 622eda1dad2a01312996dd48b812964feb64614c Mon Sep 17 00:00:00 2001 From: leslief Date: Wed, 5 Aug 2026 18:28:24 -0700 Subject: [PATCH 2/2] address comments Signed-off-by: leslief --- tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py b/tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py index 42272300c12b..d593cc5333ca 100644 --- a/tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py +++ b/tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py @@ -903,8 +903,8 @@ def __init__( # that influence tactic validity here. e.g. we are tuning FC1 and FC2 so the routing # type does not matter def unique_id(self): - return (self.top_k, self.intermediate_size, self.local_num_experts, - self.act_type) + return (self.top_k, self.num_fused_shared_experts, + self.intermediate_size, self.local_num_experts, self.act_type) def get_runner(self): instance_key = ()