From 57f7e06cb97fa46cd3dd8ace3a8321c413ee1ea5 Mon Sep 17 00:00:00 2001 From: blake-snc Date: Sun, 15 Feb 2026 08:23:51 -0800 Subject: [PATCH] fix: update Blackwell log/error messages to include SM12x (#18751) Co-authored-by: Claude Opus 4.6 --- python/sglang/srt/server_args.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py index 1fb5463c9..8c187d15f 100644 --- a/python/sglang/srt/server_args.py +++ b/python/sglang/srt/server_args.py @@ -1207,7 +1207,7 @@ class ServerArgs: if model_arch == "GlmMoeDsaForCausalLM" and is_blackwell_supported(): envs.SGLANG_NSA_FORCE_MLA.set(True) logger.warning( - "Force NSA prefill to use MLA (i.e. disable MHA_ONE_SHOT) for GlmMoeDsaForCausalLM on SM100." + "Force NSA prefill to use MLA (i.e. disable MHA_ONE_SHOT) for GlmMoeDsaForCausalLM on Blackwell." ) if self.is_attention_backend_not_set(): self.attention_backend = "nsa" @@ -1372,7 +1372,7 @@ class ServerArgs: if is_blackwell_supported() and is_mxfp4_quant_format: self.moe_runner_backend = "flashinfer_mxfp4" logger.warning( - "Detected SM100 and MXFP4 quantization format for GPT-OSS model, enabling FlashInfer MXFP4 MOE kernel." + "Detected Blackwell and MXFP4 quantization format for GPT-OSS model, enabling FlashInfer MXFP4 MOE kernel." ) elif ( is_hip() and get_bool_env_var("SGLANG_USE_AITER") @@ -1874,7 +1874,7 @@ class ServerArgs: ): if not is_blackwell_supported(): raise ValueError( - "TRTLLM MLA backend is only supported on Blackwell GPUs (SM100). Please use a different backend." + "TRTLLM MLA backend is only supported on Blackwell GPUs (SM100/SM12x). Please use a different backend." ) if self.page_size not in [32, 64]: