FlashInfer NVFP4 MoE with EP & 2-stream shared expert (#7327)

Co-authored-by: JieXin Liang <Alcanderian@users.noreply.github.com> Co-authored-by: alcanderian <alcanderian@gmail.com>
2025-06-22 13:38:47 -07:00
parent edc21cc8ae
commit 5962e70d8d
6 changed files with 182 additions and 20 deletions
--- a/python/sglang/srt/managers/schedule_batch.py
+++ b/python/sglang/srt/managers/schedule_batch.py
@@ -86,6 +86,7 @@ GLOBAL_SERVER_ARGS_KEYS = [
    "enable_deepep_moe",
    "deepep_mode",
    "enable_ep_moe",
+    "enable_flashinfer_moe",
    "moe_dense_tp_size",
    "ep_dispatch_algorithm",
    "deepep_config",