From 936220e746be62852339dfeaa0de34cd75a5132d Mon Sep 17 00:00:00 2001 From: Mandar Deshpande Date: Wed, 11 Feb 2026 21:27:04 -0800 Subject: [PATCH] [None][fix] glm engine build dtype (#11246) Signed-off-by: Mandar Deshpande --- examples/models/core/glm-4-9b/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/models/core/glm-4-9b/README.md b/examples/models/core/glm-4-9b/README.md index 9766c9124c..034e8a4239 100644 --- a/examples/models/core/glm-4-9b/README.md +++ b/examples/models/core/glm-4-9b/README.md @@ -116,7 +116,7 @@ Normally, the `trtllm-build` command only requires a single GPU, but you can ena ```bash # GLM-4-9B: single-gpu engine with dtype float16, GPT Attention plugin, Gemm plugin trtllm-build --checkpoint_dir trt_ckpt/glm_4_9b/fp16/1-gpu \ - --gemm_plugin float16 \ + --gemm_plugin bfloat16 \ --output_dir trt_engines/glm_4_9b/fp16/1-gpu ```