tests/evals/gsm8k/configs/Qwen3-Next-FP8-EP2.yaml

model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
accuracy_threshold: 0.85
num_questions: 1319
num_fewshot: 5
server_args: >-
  --max-model-len 4096
  --tensor-parallel-size 2
  --enable-expert-parallel
  --async-scheduling
  --moe-backend=flashinfer_trtllm
[CI] Add Qwen3-Next-FP8 to Blackwell model tests (#31049) Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com> 2025-12-24 05:21:50 +04:00			`model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"`
			`accuracy_threshold: 0.85`
			`num_questions: 1319`
			`num_fewshot: 5`
			`server_args: >-`
			`--max-model-len 4096`
			`--tensor-parallel-size 2`
			`--enable-expert-parallel`
			`--async-scheduling`
[UX] Add `--moe-backend` arg for explicit kernel selection (#33807) Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> 2026-02-25 20:44:44 -05:00			`--moe-backend=flashinfer_trtllm`