From 2fc480df852f406699b1432d61e9c899c6c101d5 Mon Sep 17 00:00:00 2001 From: Digant Desai Date: Fri, 17 Oct 2025 14:40:40 -0700 Subject: [PATCH] examples/qwen3: match config with optimum flow Sanity checked both flows on 1.0-rc3 and S24 --- examples/models/qwen3/config/qwen3_xnnpack_q8da4w.yaml | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/examples/models/qwen3/config/qwen3_xnnpack_q8da4w.yaml b/examples/models/qwen3/config/qwen3_xnnpack_q8da4w.yaml index 60292b1ecdc..a3cd61d621b 100644 --- a/examples/models/qwen3/config/qwen3_xnnpack_q8da4w.yaml +++ b/examples/models/qwen3/config/qwen3_xnnpack_q8da4w.yaml @@ -8,8 +8,13 @@ model: quantization: qmode: 8da4w + embedding_quantize: 8,0 + +export: + max_seq_length: 2048 + max_context_length: 2048 backend: xnnpack: enabled: True - extended_ops: True \ No newline at end of file + extended_ops: True