diff --git a/recipes/qwen3-8-flash-next-uncensored-awq-w4a16-on-2x-cmp-170hx-8-slots/recipe.yaml b/recipes/qwen3-8-flash-next-uncensored-awq-w4a16-on-2x-cmp-170hx-8-slots/recipe.yaml index c2d17f3d2..4500d899d 100644 --- a/recipes/qwen3-8-flash-next-uncensored-awq-w4a16-on-2x-cmp-170hx-8-slots/recipe.yaml +++ b/recipes/qwen3-8-flash-next-uncensored-awq-w4a16-on-2x-cmp-170hx-8-slots/recipe.yaml @@ -124,3 +124,5 @@ provenance: - name: 'wtdcode (vllm-backport)' url: 'https://github.com/wtdcode/vllm-backport' +max_context_len: 262144 +kv_pool_tokens: 897000