Yuan Luo af6bcadcf7 [VLM] Support Piecewise CUDA Graph for Qwen2.5-VL (#13055) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: Yuhao Yang <yhyang201@gmail.com>

2025-11-20 10:23:44 +08:00

..

nightly_utils.py

Implement nightly test workflow naming conventions (#13170)

2025-11-14 16:14:53 -08:00

test_deepseek_v31_perf.py

Fix 8-gpu B200 nightly tests (#13457)

2025-11-17 13:26:56 -08:00

test_deepseek_v32_perf.py

Fix 8-gpu B200 nightly tests (#13457)

2025-11-17 13:26:56 -08:00

test_encoder_dp.py

[VLM][feat] Support encoder DP for Qwen2.5-VL (#13126)

2025-11-18 16:13:18 +08:00

test_flashinfer_trtllm_gen_attn_backend.py

Re-enable Flashinfer TRTLLM GEN MHA and Add Unit Test (#12885)

2025-11-10 20:17:43 -08:00

test_flashinfer_trtllm_gen_moe_backend.py

Enable Flashinfer TRTLLM-GEN-MoE FP8 blockwise kernel for Qwen3-Next on Blackwell (#12543)

2025-11-13 19:44:44 +08:00

test_gpt_oss_4gpu_perf.py

…

test_gsm8k_eval_amd.py

Extend lint test to test/ directory (#13247)

2025-11-14 00:01:48 -08:00

test_text_models_gsm8k_eval.py

…

test_text_models_perf.py

…

test_vlms_mmmu_eval.py

…

test_vlms_perf.py

…

test_vlms_piecewise_cuda_graph.py

[VLM] Support Piecewise CUDA Graph for Qwen2.5-VL (#13055)

2025-11-20 10:23:44 +08:00