kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

fix:https://nvbugs/5298661 (#5022)

Browse Source 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
This commit is contained in:
nv-guomingz 2025-06-12 20:41:44 +08:00 committed by GitHub
parent 58d4ca2385
commit cf35a079f9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/integration/defs/examples/test_mistral.py
View File

@ -20,7 +20,7 @@ import psutil
import pytest
from defs.common import (convert_weights, quantize_data,
test_multi_lora_support, venv_check_call)
from defs.conftest import skip_pre_ada
from defs.conftest import skip_post_blackwell, skip_pre_ada
from defs.trt_test_alternative import check_call
@ -58,6 +58,7 @@ def mistral_example_root(llm_venv):
check_call(" ".join(install_cmd), shell=True, env=llm_venv._new_env)
@skip_post_blackwell #nvbug 5298661
@pytest.mark.parametrize(
"run_type",
['inference', 'summarization_long', 'chunked_summarization_long'])

4
tests/integration/test_lists/waives.txt
View File

@ -50,7 +50,6 @@ full:B200_PCIe/examples/test_mamba.py::test_llm_mamba_1gpu[mamba2-130m-float16-d
full:B200_PCIe/examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-enable_gemm_plugin] SKIP (Disable for Blackwell)
full:B200_PCIe/examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-disable_gemm_plugin] SKIP (Disable for Blackwell)
full:B200_PCIe/examples/test_medusa.py::test_llm_medusa_1gpu[use_cpp_session-medusa-vicuna-7b-v1.3-4-heads-bfloat16-bs1] SKIP (Disable for Blackwell)
full:B200_PCIe/examples/test_mistral.py::test_llm_mistral_v1_1gpu[mistral-7b-v0.1-float16-max_attention_window_size_4096-summarization_long] SKIP (Disable for Blackwell)
full:B200_PCIe/examples/test_llama.py::test_llm_llama_v2_1gpu_gemm_swiglu[llama-v2-7b-hf-fp8-float16] SKIP (Disable for Blackwell)
full:B200_PCIe/examples/test_llama.py::test_llm_llama_int8_kv_1gpu_summary[llama-7b-enable_weight_only-nb:4] SKIP (Disable for Blackwell)
full:B200_PCIe/examples/test_llama.py::test_llm_llama_int8_sq_ootb_1gpu_summary[llama-7b-nb:1] SKIP (Disable for Blackwell)
@ -125,7 +124,6 @@ full:B200/examples/test_mamba.py::test_llm_mamba_1gpu[mamba2-130m-float16-disabl
full:B200/examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-enable_gemm_plugin] SKIP (Disable for Blackwell)
full:B200/examples/test_mamba.py::test_llm_mamba_1gpu[mamba-codestral-7B-v0.1-float16-disable_gemm_plugin] SKIP (Disable for Blackwell)
full:B200/examples/test_medusa.py::test_llm_medusa_1gpu[use_cpp_session-medusa-vicuna-7b-v1.3-4-heads-bfloat16-bs1] SKIP (Disable for Blackwell)
full:B200/examples/test_mistral.py::test_llm_mistral_v1_1gpu[mistral-7b-v0.1-float16-max_attention_window_size_4096-summarization_long] SKIP (Disable for Blackwell)
full:B200/examples/test_llama.py::test_llm_llama_v2_1gpu_gemm_swiglu[llama-v2-7b-hf-fp8-float16] SKIP (Disable for Blackwell)
full:B200/examples/test_llama.py::test_llm_llama_int8_kv_1gpu_summary[llama-7b-enable_weight_only-nb:4] SKIP (Disable for Blackwell)
full:B200/examples/test_llama.py::test_llm_llama_int8_sq_ootb_1gpu_summary[llama-7b-nb:1] SKIP (Disable for Blackwell)
@ -427,7 +425,7 @@ test_e2e.py::test_ptp_quickstart_advanced_ngram[Llama-3.1-8B-Instruct-llama-3.1-
unittest/_torch/auto_deploy/integration/test_ad_build.py SKIP (https://nvbugs/5318103)
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=TRTLLM-torch_compile=False] SKIP (https://nvbugs/5318143)
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp2pp2-attn_backend=TRTLLM-torch_compile=True] SKIP (https://nvbugs/5318143)
examples/test_mistral.py::test_llm_mistral_v1_1gpu[mistral-7b-v0.1-float16-max_attention_window_size_4096-summarization_long] SKIP (https://nvbugs/5324976)
test_e2e.py::test_openai_reasoning SKIP (https://nvbugs/5310329)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=False] SKIP (https://nvbugs/5322354)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=True] SKIP (https://nvbugs/5322354)
accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=False] SKIP (https://nvbugs/5322354)