[Refactor] Add -fp4-gemm-backend to replace SGLANG_FLASHINFER_FP4_GEMM_BACKEND (#16534)

Co-authored-by: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>
This commit is contained in:
b8zhong
2026-01-18 23:25:46 +08:00
committed by GitHub
co-authored by Vincent Zhong
parent f3a7c7dcd9
commit 4df74eb576
9 changed files with 144 additions and 18 deletions
+4
View File
@@ -503,6 +503,10 @@ _warn_deprecated_env_to_cli_flag(
"SGLANG_SUPPORT_CUTLASS_BLOCK_FP8",
"It will be completely removed in 0.5.7. Please use '--fp8-gemm-backend=cutlass' instead.",
)
_warn_deprecated_env_to_cli_flag(
"SGLANG_FLASHINFER_FP4_GEMM_BACKEND",
"It will be completely removed in 0.5.9. Please use '--fp4-gemm-backend' instead.",
)
_warn_deprecated_env_to_cli_flag(
"SGLANG_SCHEDULER_DECREASE_PREFILL_IDLE",
"Please use '--enable-prefill-delayer' instead.",