Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 0 additions & 1 deletion tests/integration/test_lists/waives.txt
Original file line number Diff line number Diff line change
Expand Up @@ -358,7 +358,6 @@ unittest/_torch/thop/serial/test_moe.py::TestMoeFp4::test_no_autotune[use_score_
unittest/_torch/thop/serial/test_moe.py::TestMoeFp4::test_no_autotune[use_score_as_input-RoutingRenormalize_qwen_next-swiglu-1024-1024-150] SKIP (https://nvbugs/5908070)
unittest/_torch/thop/serial/test_moe.py::TestMoeFp4::test_no_autotune[use_score_as_input-RoutingRenormalize_topk_4-swiglu-1024-1024-150] SKIP (https://nvbugs/5908070)
unittest/_torch/visual_gen/test_flux_pipeline.py::TestFluxCombinedOptimizations::test_all_optimizations_combined SKIP (https://nvbugs/6199854)
unittest/auto_deploy/singlegpu/shim/test_llm_config.py::test_speculative_flashinfer_fallback_disables_piecewise SKIP (https://nvbugs/6309375)
unittest/auto_deploy/singlegpu/smoke SKIP (https://nvbugs/6306936)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_batch_smoke[deepseek-trtllm-simple] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_batch_smoke[llama-flashinfer-cudagraph] SKIP (https://nvbugs/6307525)
Expand Down
19 changes: 0 additions & 19 deletions tests/unittest/auto_deploy/singlegpu/shim/test_llm_config.py
Original file line number Diff line number Diff line change
Expand Up @@ -95,25 +95,6 @@ def test_yaml_compile_backend_disables_default_piecewise(tmp_path):
assert args.transforms["compile_model"]["piecewise_enabled"] is False


def test_speculative_flashinfer_fallback_disables_piecewise():
from tensorrt_llm.llmapi import EagleDecodingConfig

spec_config = EagleDecodingConfig(
max_draft_len=3,
speculative_model="some/model",
eagle3_one_model=True,
)

args = LlmArgs(
model="test-model",
attn_backend="flashinfer",
speculative_config=spec_config,
)

assert args.compile_backend == "torch-simple"
assert args.transforms["compile_model"]["piecewise_enabled"] is False


def test_cache_transceiver_rejects_unmanaged_persistent_caches():
"""Cache transceiver rejects unmanaged persistent cache resources."""
args = LlmArgs(
Expand Down
Loading