[Feature]Support ragged prefill in flashinfer mla backend (#3967)

Co-authored-by: Yineng Zhang <me@zhyncs.com> Co-authored-by: pankajroark <pankajroark@users.noreply.github.com>
2025-02-28 18:13:56 -08:00
parent f3b99f73b3
commit 90a4b7d98a
9 changed files with 308 additions and 407 deletions
--- a/python/sglang/srt/model_executor/model_runner.py
+++ b/python/sglang/srt/model_executor/model_runner.py
@@ -182,6 +182,7 @@ class ModelRunner:
                "device": server_args.device,
                "enable_flashinfer_mla": server_args.enable_flashinfer_mla,
                "disable_radix_cache": server_args.disable_radix_cache,
+                "flashinfer_mla_disable_ragged": server_args.flashinfer_mla_disable_ragged,
            }
        )