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

test: add qa test list for rtx5090 and rtx_pro_6000 (#4254)

Browse Source 
* add test list for rtx5090 and rtx_pro_6000

Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>

* add 2gpu llama70b test cases

Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>

* remove duplicate and invalid test cases

Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>

* add 2gpus test cases

Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>

---------

Signed-off-by: Stanley Sun <190317771+StanleySun639@users.noreply.github.com>
This commit is contained in:
Stanley Sun 2025-05-15 17:57:31 +08:00 committed by GitHub
parent d6b741ddfe
commit 9d3e05486b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 57 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
tests/integration/test_lists/qa/llm_release_gb20x.txt Normal file
View File

@ -0,0 +1,28 @@
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-BF16-llama-3.1-model/Meta-Llama-3.1-8B]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.2-11B-BF16-llama-3.2-models/Llama-3.2-11B-Vision]
test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-image]
test_e2e.py::test_ptp_quickstart_multimodal[NVILA-8B-FP16-vila/NVILA-8B-video]
test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-image]
test_e2e.py::test_ptp_quickstart_multimodal[qwen2-vl-7b-instruct-Qwen2-VL-7B-Instruct-video]
test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-image]
test_e2e.py::test_ptp_quickstart_multimodal[qwen2.5-vl-7b-instruct-Qwen2.5-VL-7B-Instruct-video]
examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-full_prec]
examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-int4_awq]
examples/test_nemotron.py::test_llm_nemotron_4_15b_1gpu[bfloat16-fp8]
examples/test_nemotron.py::test_llm_nemotron_4_15b_1gpu[bfloat16-full_prec]
examples/test_llama.py::test_llama_3_x_fp8_with_bf16_lora[llama-3.2-1b]
examples/test_llama.py::test_llama_3_x_fp8_with_bf16_lora[llama-3.2-3b]
examples/test_llama.py::test_mistral_nemo_fp8_with_bf16_lora[Mistral-Nemo-12b-Base]
examples/test_multimodal.py::test_llm_multimodal_general[Llama-3.2-11B-Vision-pp:1-tp:1-bfloat16-bs:1-cpp_e2e:False-nb:1]
examples/test_multimodal.py::test_llm_multimodal_general[Llama-3.2-11B-Vision-pp:1-tp:1-bfloat16-bs:8-cpp_e2e:False-nb:1]
examples/test_mistral.py::test_llm_mistral_lora_1gpu[komt-mistral-7b-v1-lora-komt-mistral-7b-v1]
examples/test_mistral.py::test_llm_mistral_v1_1gpu[mistral-7b-v0.1-float16-max_attention_window_size_4096-summarization_long]
examples/test_mistral.py::test_mistral_nemo_minitron_fp8_with_bf16_lora[Mistral-NeMo-Minitron-8B-Instruct]
examples/test_mixtral.py::test_llm_mixtral_int4_awq_1gpu_summary[mixtral-8x7b-v0.1-AWQ]
examples/test_enc_dec.py::test_llm_enc_dec_general[compare_hf-byt5-small-float32-enable_gemm_plugin-enable_attention_plugin-enable_paged_kv_cache-tp:1-pp:1-nb:1-enable_fp8]
examples/test_enc_dec.py::test_llm_enc_dec_general[compare_hf-flan-t5-small-float32-enable_gemm_plugin-enable_attention_plugin-enable_paged_kv_cache-tp:1-pp:1-nb:1-disable_fp8]
examples/test_enc_dec.py::test_llm_enc_dec_general[compare_hf-t5-small-float32-enable_gemm_plugin-enable_attention_plugin-enable_paged_kv_cache-tp:1-pp:1-nb:1-disable_fp8]
accuracy/test_cli_flow.py::TestStarcoder2_3B::test_auto_dtype
accuracy/test_cli_flow.py::TestStarcoder2_15B::test_smooth_quant_ootb

29
tests/integration/test_lists/qa/llm_release_rtx_pro_6000.txt Normal file
View File

@ -0,0 +1,29 @@
accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp8_tp2pp2
accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp8_tp2pp2_manage_weights
accuracy/test_cli_flow.py::TestMixtral8x7B::test_nvfp4_prequantized
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=True-cuda_graph=False-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=True-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=True]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=True-cuda_graph=True-overlap_scheduler=True]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=False-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=False-cuda_graph=True-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=True]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[fp8kv=True-attention_dp=False-cuda_graph=False-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[fp8kv=False-attention_dp=True-cuda_graph=False-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[fp8kv=False-attention_dp=False-cuda_graph=True-overlap_scheduler=False]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=True]
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True]
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B::test_nvfp4
test_e2e.py::test_ptp_quickstart_advanced_mixed_precision
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-BF16-llama-3.1-model/Meta-Llama-3.1-8B]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-70B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-70B]
test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-70B-FP8-llama-3.1-model/Llama-3.1-70B-Instruct-FP8]
test_e2e.py::test_ptp_quickstart_advanced[Mixtral-8x7B-NVFP4-nvfp4-quantized/Mixtral-8x7B-Instruct-v0.1]
test_e2e.py::test_ptp_quickstart_advanced_2gpus_sm120[Llama3.1-70B-BF16-llama-3.1-model/Meta-Llama-3.1-70B]
test_e2e.py::test_ptp_quickstart_advanced_2gpus_sm120[Mixtral-8x7B-BF16-Mixtral-8x7B-Instruct-v0.1]