Fix nightly ci Gsm8k & Fix flashinfer backend kvcache quant (#4147)

2025-03-07 03:50:07 +08:00
parent bc1534ff32
commit ab7fba0ece
1 changed files with 1 additions and 0 deletions
--- 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,
        )