From ab7fba0ecee3a40dfce04f37e6c179e4ef515c38 Mon Sep 17 00:00:00 2001 From: yinfan98 <1106310035@qq.com> Date: Fri, 7 Mar 2025 03:50:07 +0800 Subject: [PATCH] Fix nightly ci Gsm8k & Fix flashinfer backend kvcache quant (#4147) --- python/sglang/srt/layers/attention/flashinfer_backend.py | 1 + 1 file changed, 1 insertion(+) diff --git a/python/sglang/srt/layers/attention/flashinfer_backend.py b/python/sglang/srt/layers/attention/flashinfer_backend.py index de3bbe5cf..af47f2ce2 100644 --- a/python/sglang/srt/layers/attention/flashinfer_backend.py +++ b/python/sglang/srt/layers/attention/flashinfer_backend.py @@ -904,6 +904,7 @@ class FlashInferIndicesUpdaterPrefill: self.head_dim, 1, q_data_type=self.q_data_type, + kv_data_type=self.data_type, custom_mask=custom_mask, non_blocking=True, )