mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
[None][infra] Waive failed cases again on 1/5 (#10403)
Signed-off-by: qqiao <qqiao@nvidia.com>
This commit is contained in:
parent
e7a4486294
commit
c63fad7d96
@ -541,3 +541,5 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[throughp
|
||||
perf/test_perf_sanity.py::test_e2e[disagg_upload-deepseek-r1-fp4_1k1k_ctx1_gen1_dep8_bs768_eplb0_mtp0_ccb-UCX] SKIP (https://nvbugs/5778381)
|
||||
unittest/_torch/attention/test_flashinfer_star_attn.py::TestStarAttention::test_flashinfer_star_attention[num_layers:2-num_heads:32-num_kv_heads:8-head_dim:64-anchor_size:64-block_size:64-dtype:torch.float16] SKIP (https://nvbugs/5781389)
|
||||
unittest/_torch/ray_orchestrator/multi_gpu/test_ops.py::test_reducescatter_pg_op[var_len:True-seqlen:16-hidden:128] SKIP (https://nvbugs/5781383)
|
||||
cpp/test_e2e.py::test_model[-mamba-86] SKIP (https://nvbugs/5781665)
|
||||
unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_tinyllama_logits_processor_tp2pp2 SKIP (https://nvbugs/5781731)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user