Add fp4 quantize before all-gather for Flashinfer cutlass MoE DP (max throughput) (#7667)

2025-08-15 22:08:11 -07:00
parent 87dab54824
commit eff4eb3fdd
16 changed files with 360 additions and 52 deletions
--- a/python/sglang/srt/managers/schedule_batch.py
+++ b/python/sglang/srt/managers/schedule_batch.py
@@ -84,6 +84,7 @@ GLOBAL_SERVER_ARGS_KEYS = [
    "chunked_prefill_size",
    "device",
    "disable_chunked_prefix_cache",
+    "disable_flashinfer_cutlass_moe_fp4_allgather",
    "disable_radix_cache",
    "enable_dp_lm_head",
    "enable_flashinfer_allreduce_fusion",