Skip to content

Commit d6d160f

Browse files
lfr-0531longlee0622
authored andcommitted
[None][chore] Move the rocketkv e2e test to post-merge (NVIDIA#9768)
Signed-off-by: Fanrong Li <[email protected]>
1 parent 01c0539 commit d6d160f

File tree

3 files changed

+3
-3
lines changed

3 files changed

+3
-3
lines changed

tests/integration/defs/accuracy/references/longbench_v2.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,5 +8,5 @@ DeepSeek-R1-0528:
88
spec_dec_algo: MTP
99
accuracy: 52.093
1010
meta-llama/Llama-3.1-8B-Instruct:
11-
- accuracy: 26.48
11+
- accuracy: 26.00
1212
sigma: 25.8

tests/integration/defs/accuracy/test_llm_api_pytorch.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4594,7 +4594,7 @@ def test_auto_dtype(self):
45944594

45954595

45964596
@skip_pre_blackwell
4597-
class TestLlama3_1_8B_Instruct_LongBenchV2(LlmapiAccuracyTestHarness):
4597+
class TestLlama3_1_8B_Instruct_RocketKV(LlmapiAccuracyTestHarness):
45984598
MODEL_NAME = "meta-llama/Llama-3.1-8B-Instruct"
45994599
MODEL_PATH = f"{llm_models_root()}/llama-3.1-model/Llama-3.1-8B-Instruct/"
46004600

tests/integration/test_lists/test-db/l0_b200.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,6 @@ l0_b200:
5656
- accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-CUTLASS]
5757
- accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a16_mxfp4[latency-TRTLLM]
5858
- accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_nvfp4[tp1-cutlass]
59-
- accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B_Instruct_LongBenchV2::test_auto_dtype
6059
- disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0] # nvbugs 5300551
6160
- test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B]
6261
- test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]
@@ -157,3 +156,4 @@ l0_b200:
157156
- accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=TRTLLM-mtp_nextn=2-fp8kv=False-attention_dp=False-cuda_graph=True-overlap_scheduler=False-torch_compile=False]
158157
- accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTEDSL-mtp_nextn=0-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False]
159158
- accuracy/test_llm_api_pytorch.py::TestSeedOss_36B::test_auto_dtype
159+
- accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B_Instruct_RocketKV::test_auto_dtype

0 commit comments

Comments
 (0)