Skip to content

[https://nvbugs/6525059][fix] Drop 8 from FP8BlockScaleMoeRunner::mSupportedTileN, covering both the… #17135

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
trtllm-agent wants to merge 2 commits into
base: main
Choose a base branch
from
+7 −4
Open

[https://nvbugs/6525059][fix] Drop 8 from FP8BlockScaleMoeRunner::mSupportedTileN, covering both the… #17135

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dc195a8
[nvbugs/6525059][fix] Drop broken tileN=8 tactic from FP8 block-scale…
trtllm-agent Jul 31, 2026
7cf564a
[nvbugs/6525059][chore] Remove stale waiver after fix
trtllm-agent Aug 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion cpp/tensorrt_llm/thop/fp8BlockScaleMoe.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -384,7 +384,13 @@ class FP8BlockScaleMoeRunner : public torch::CustomClassHolder

public:
explicit FP8BlockScaleMoeRunner()
: mSupportedTileN{8, 16, 32, 64, 128}
// tileN=8 is excluded: every DeepSeek-FP8 GEMM2 cubin at that tile faults with
// cudaErrorIllegalAddress in its epilogue store on sm100f/sm103, so the tile size is
// broken rather than a single cubin (https://nvbugs/6525059). Dropping it here rather
// than in TrtllmGenBatchedGemmRunner::skipQuirks both raises the fallback clamp floor
// below and avoids constructing a tileN=8 runner, which would throw on an empty
// passing-config list.
: mSupportedTileN{16, 32, 64, 128}
Comment thread
coderabbitai[bot] marked this conversation as resolved.
{
for (int tileN : mSupportedTileN)
{
Expand Down
3 changes: 0 additions & 3 deletions tests/integration/test_lists/waives.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -163,7 +163,6 @@ full:B200/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_nvfp4[use_msa=Fa
full:B200/accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_4gpus_block_reuse[ADP4] SKIP (https://nvbugs/6525008)
full:B200/accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_4gpus_block_reuse[ADP4_MTP] SKIP (https://nvbugs/6525008)
full:B200/accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_4gpus_block_reuse[TEP4] SKIP (https://nvbugs/6474894)
full:B200/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_dummy_load_format SKIP (https://nvbugs/6525059)
full:B200/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-deepseek_r1_v2_fp4_stress] SKIP (https://nvbugs/6472256)
full:B200/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-glm5_nvfp4_tp4_ep4_dp_stress] SKIP (https://nvbugs/6544407)
full:B200/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-qwen3_32b_fp8_stress] SKIP (https://nvbugs/6472256)
Expand Down Expand Up @@ -215,7 +214,6 @@ full:GB200/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_nvfp4[use_msa=F
full:GB200/accuracy/test_llm_api_pytorch.py::TestMinistral8BInstruct::test_auto_dtype SKIP (https://nvbugs/6547151)
full:GB200/accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_4gpus_block_reuse[ADP4] SKIP (https://nvbugs/6474894)
full:GB200/accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_4gpus_static_eplb[moe_backend=TRTLLM] SKIP (https://nvbugs/6525898)
full:GB200/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_dummy_load_format SKIP (https://nvbugs/6525059)
full:GB200/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=True] SKIP (https://nvbugs/5929339)
full:GB200/accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_fp8_moe_dflash SKIP (https://nvbugs/6316985)
full:GB200/accuracy/test_llm_api_pytorch.py::TestQwen3_5_397B_A17B::test_nvfp4_4gpus_online_eplb[moe_backend=TRTLLM] SKIP (https://nvbugs/6462928)
Expand Down Expand Up @@ -245,7 +243,6 @@ full:GB300/accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4
full:GB300/accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[tp4-fp8kv=False-attn_backend=FLASHINFER-torch_compile=True] SKIP (https://nvbugs/6473161)
full:GB300/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_mxfp8[use_msa=False] SKIP (https://nvbugs/6422502)
full:GB300/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_nvfp4[use_msa=False] SKIP (https://nvbugs/6422502)
full:GB300/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_dummy_load_format SKIP (https://nvbugs/6525059)
full:GB300/accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_fp8_moe_dflash SKIP (https://nvbugs/6316985)
full:GB300/accuracy/test_llm_api_pytorch_multimodal.py::TestGemma3_27BInstruct::test_fp8_prequantized SKIP (https://nvbugs/6479708)
full:GB300/accuracy/test_llm_api_pytorch_multimodal.py::TestQwen3_5_35B_A3B_VL::test_fp8_prequantized SKIP (https://nvbugs/6526429)
Expand Down
Loading