mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
[None][fix] Solve pillow version conflict (#10537)
Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
This commit is contained in:
parent
3bd319dc8e
commit
11da7e3605
@ -10,7 +10,7 @@ tiktoken
|
||||
einops
|
||||
|
||||
# optional dependencies
|
||||
gradio==4.44.1
|
||||
gradio==5.4.0
|
||||
mdtex2html
|
||||
sse_starlette
|
||||
aiohttp_sse_client
|
||||
|
||||
@ -260,6 +260,7 @@ class TestQwen3VL_MOE(LlmapiAccuracyTestHarness):
|
||||
max_tokens=MAX_NUM_TOKENS, truncate_prompt_tokens=MMMU.MAX_INPUT_LEN, stop="<|endoftext|>"
|
||||
)
|
||||
|
||||
@pytest.mark.skip_less_device_memory(140000)
|
||||
def test_auto_dtype(self):
|
||||
with LLM(
|
||||
self.MODEL_PATH,
|
||||
|
||||
@ -220,8 +220,6 @@ examples/test_phi.py::test_llm_phi_quantization_1gpu[Phi-3-small-128k-instruct-f
|
||||
examples/test_multimodal.py::test_llm_multimodal_general[Mistral-Small-3.1-24B-Instruct-2503-pp:1-tp:1-bfloat16-bs:8-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5644684)
|
||||
accuracy/test_llm_api_pytorch.py::TestLlama3_1NemotronNano8Bv1::test_fp8_prequantized SKIP (https://nvbugs/5640697)
|
||||
accuracy/test_llm_api_pytorch.py::TestQwQ_32B::test_auto_dtype_tp4 SKIP (https://nvbugs/5640697)
|
||||
accuracy/test_llm_api_pytorch_multimodal.py::TestNVILA_8B::test_auto_dtype SKIP (https://nvbugs/5648441)
|
||||
accuracy/test_llm_api_pytorch_multimodal.py::TestVILA1_5_3B::test_auto_dtype SKIP (https://nvbugs/5648441)
|
||||
test_e2e.py::test_trtllm_multimodal_benchmark_serving SKIP (https://nvbugs/5647825)
|
||||
unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[MNNVL] SKIP (https://nvbugs/5664904)
|
||||
unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[DeepEP] SKIP (https://nvbugs/5664904)
|
||||
@ -233,7 +231,6 @@ test_e2e.py::test_ptp_quickstart_advanced[Nemotron-Super-49B-v1-NVFP4-nvfp4-quan
|
||||
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-cutlass-auto] SKIP (https://nvbugs/5673610)
|
||||
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass-auto] SKIP (https://nvbugs/5756804)
|
||||
examples/test_llama.py::test_llm_llama_1gpu_fp4[llama-3.1-70b-instruct-enable_norm_quant_fusion-enable_fused_quant-fp4_plugin-bfloat16] SKIP (https://nvbugs/5451216)
|
||||
accuracy/test_llm_api_pytorch_multimodal.py::TestNemotron_Nano_12B_V2_VL::test_auto_dtype SKIP (https://nvbugs/5588376)
|
||||
accuracy/test_llm_api_pytorch.py::TestNemotronNas::test_auto_dtype_tp8 SKIP (https://nvbugs/5673527)
|
||||
unittest/_torch/auto_deploy/unit/multigpu/test_ad_build_small_multi.py::test_build_ad[meta-llama/Meta-Llama-3.1-8B-Instruct-llm_extra_args0-2] SKIP (https://nvbugs/5680755)
|
||||
full:H100_PCIe/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_multi_lora_evict_and_reload_lora_gpu_cache SKIP (https://nvbugs/5682551)
|
||||
@ -257,9 +254,6 @@ accuracy/test_cli_flow.py::TestGpt2::test_int8_kv_cache SKIP (https://nvbugs/570
|
||||
accuracy/test_cli_flow.py::TestLlama2_7B::test_fp8_2gpus[cp2] SKIP (https://nvbugs/5705194)
|
||||
accuracy/test_cli_flow.py::TestLlama2_7B::test_smooth_quant_ootb_tp2 SKIP (https://nvbugs/5705195)
|
||||
accuracy/test_cli_flow.py::TestTinyLlama1_1BChat::test_weight_only_int8_kv_cache[int8] SKIP (https://nvbugs/5666826)
|
||||
accuracy/test_llm_api_pytorch_multimodal.py::TestQwen2_5_VL_7B::test_auto_dtype SKIP (https://nvbugs/5707087)
|
||||
accuracy/test_llm_api_pytorch_multimodal.py::TestLlava_V1_6_Mistral_7B::test_auto_dtype SKIP (https://nvbugs/5707087)
|
||||
accuracy/test_llm_api_pytorch_multimodal.py::TestPhi4MMFusedVisionLora::test_auto_dtype SKIP (https://nvbugs/5707087)
|
||||
disaggregated/test_disaggregated.py::test_disaggregated_ctxtp2pp2_gentp2pp2[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/5705199)
|
||||
accuracy/test_llm_api_pytorch.py::TestLlama3_3NemotronSuper49Bv1::test_auto_dtype_tp2 SKIP (https://nvbugs/5707145)
|
||||
accuracy/test_llm_api_pytorch.py::TestLlama3_3NemotronSuper49Bv1::test_fp8_prequantized_tp2 SKIP (https://nvbugs/5707145)
|
||||
@ -295,7 +289,6 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus_online_ep
|
||||
cpp/test_multi_gpu.py::TestDisagg::test_symmetric_executor[gpt-2proc-mpi_kvcache-90] SKIP (https://nvbugs/5755941)
|
||||
examples/test_granite.py::test_llm_granite[granite-3.0-1b-a400m-instruct-bfloat16] SKIP (https://nvbugs/5608979)
|
||||
examples/test_granite.py::test_llm_granite[granite-3.0-2b-instruct-bfloat16] SKIP (https://nvbugs/5608979)
|
||||
accuracy/test_llm_api_pytorch_multimodal.py::TestQwen3VL_MOE::test_auto_dtype SKIP (https://nvbugs/5588376)
|
||||
unittest/executor/test_base_worker.py::TestWorkerBase SKIP (https://nvbugs/5759698)
|
||||
triton_server/test_triton.py::test_gpt_disaggregated_serving_bls[gpt-disaggregated-serving-bls] SKIP (https://nvbugs/5582118)
|
||||
cpp/test_multi_gpu.py::test_cache_transceiver[8proc-mooncake_kvcache-90] SKIP (https://nvbugs/5760737)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user