[NVIDIA][test] Tests for flashinfer TRTLLM BF16 MoE (#33715)

Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>
This commit is contained in:
Linda
2026-02-11 12:38:11 +00:00
committed by GitHub
co-authored by Pavani Majety
parent 0f5e55e7a8
commit 275e0d2a99
7 changed files with 296 additions and 1 deletions
@@ -5,3 +5,5 @@ num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --enable-expert-parallel"
env:
VLLM_USE_FLASHINFER_MOE_FP16: "1"
VLLM_FLASHINFER_MOE_BACKEND: "throughput"
@@ -5,3 +5,4 @@ num_fewshot: 5
server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --enable-expert-parallel"
env:
VLLM_USE_FLASHINFER_MOE_FP16: "1"
VLLM_FLASHINFER_MOE_BACKEND: "throughput"