diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 9aaf4b5475bf..057df7d91452 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -256,15 +256,6 @@ unittest/_torch/attention/sparse/dsa/test_req_idx_per_token.py::test_on_update_k unittest/_torch/attention/test_attention_backends.py::test_attention_backend[exaone_moe_gqa_swa128-ctx-bf16-HND-p32-v1] SKIP (https://nvbugs/6668773) unittest/_torch/attention/test_attention_backends.py::test_attention_backend[qwen2_0_5b_gqa_hd64-ctx-bf16-HND-p32-v1] SKIP (https://nvbugs/6641268) unittest/_torch/executor/kv_cache/test_kv_cache_budget_split.py::TestSplitGpuBudgetForDraft::test_target_cost_uses_derived_layer_type_windows SKIP (https://nvbugs/6800223) -unittest/_torch/executor/kv_cache/test_kv_cache_manager_v2.py::test_prepare_context_drops_cached_token_attribution_while_estimating SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) -unittest/_torch/executor/kv_cache/test_kv_cache_manager_v2.py::test_prepare_context_keeps_cached_token_attribution_staged_by_the_core SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) -unittest/_torch/executor/test_kv_connector_v2_prefix.py::TestAskTiming::test_the_scheduling_pass_does_not_ask SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) -unittest/_torch/executor/test_kv_connector_v2_prefix.py::TestReEntryAfterAServe::test_a_dead_allocation_drops_the_floor SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) -unittest/_torch/executor/test_kv_connector_v2_prefix.py::TestReEntryAfterAServe::test_the_chunk_still_spans_to_the_end_of_the_prompt SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) -unittest/_torch/executor/test_kv_connector_v2_prefix.py::TestReEntryAfterAServe::test_the_same_holds_for_a_synchronous_serve SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) -unittest/_torch/executor/test_kv_connector_v2_prefix.py::TestReEntryAfterAServe::test_the_served_position_survives_re_entry SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) -unittest/_torch/executor/test_kv_connector_v2_prefix.py::TestSwaScratchReuse::test_scratch_reuse_is_disabled_before_the_scheduler_can_take_slots SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) -unittest/_torch/executor/test_kv_connector_v2_prefix.py::TestSwaScratchReuse::test_scratch_reuse_survives_without_a_connector SKIP (https://github.com/NVIDIA/TensorRT-LLM/pull/19382) unittest/_torch/modeling/test_gemma4_e2e_dummy.py::test_e2e_text_31b_dummy SKIP (https://nvbugs/6607482) unittest/_torch/modeling/test_modeling_nemotron_h.py::test_nemotron_h_breakable_prefill_cuda_graph -k "tp1" SKIP (https://nvbugs/6797747) unittest/_torch/modeling/test_modeling_nemotron_h.py::test_nemotron_h_breakable_prefill_cuda_graph -k "tp2" SKIP (https://nvbugs/6797215) diff --git a/tests/unittest/_torch/executor/kv_cache/test_kv_cache_manager_v2.py b/tests/unittest/_torch/executor/kv_cache/test_kv_cache_manager_v2.py index e979dd8197ca..79448809462d 100644 --- a/tests/unittest/_torch/executor/kv_cache/test_kv_cache_manager_v2.py +++ b/tests/unittest/_torch/executor/kv_cache/test_kv_cache_manager_v2.py @@ -1831,6 +1831,7 @@ def _make_admission_manager( """ manager = object.__new__(KVCacheManagerV2) manager.conversation_manager = None + manager.kv_connector_manager = None manager.enable_block_reuse = True manager.tokens_per_block = TOKENS_PER_BLOCK manager.is_draft = False diff --git a/tests/unittest/_torch/executor/test_kv_connector_v2_prefix.py b/tests/unittest/_torch/executor/test_kv_connector_v2_prefix.py index f35e33dd6e6a..89d7b991f74e 100644 --- a/tests/unittest/_torch/executor/test_kv_connector_v2_prefix.py +++ b/tests/unittest/_torch/executor/test_kv_connector_v2_prefix.py @@ -201,6 +201,7 @@ def make_manager(connector, num_extra_kv_tokens=0, is_draft=False): manager = object.__new__(KVCacheManagerV2) manager.kv_connector_manager = connector manager.is_draft = is_draft + manager.is_estimating_kv_cache = False manager.tokens_per_block = TOKENS_PER_BLOCK manager.num_extra_kv_tokens = num_extra_kv_tokens manager.kv_cache_map = {}