From fa0792a0aa22b97926c5633fa875991d8ca898d9 Mon Sep 17 00:00:00 2001 From: chickeyton Date: Sun, 29 Mar 2026 23:56:51 +0800 Subject: [PATCH] [Doc] Add transformers version requirement in GLM-Image example doc (#2265) Signed-off-by: chickeyton --- examples/offline_inference/glm_image/README.md | 9 +++++++++ examples/online_serving/glm_image/README.md | 6 ++++++ 2 files changed, 15 insertions(+) diff --git a/examples/offline_inference/glm_image/README.md b/examples/offline_inference/glm_image/README.md index 1e7e75144..c3c7c2916 100644 --- a/examples/offline_inference/glm_image/README.md +++ b/examples/offline_inference/glm_image/README.md @@ -129,8 +129,17 @@ The first run loads model weights. Subsequent runs are faster: --stage-init-timeout 900 # Increase timeout for slow storage ``` +### `Transformers does not recognize this architecture` Error + +Your have to upgrade `transformers` package to `5.3.0` or above: + +``` +pip install --upgrade transformers +``` + ## Requirements - vLLM-Omni with GLM-Image support - CUDA-capable GPU (recommended: H100/A100 with 80GB) - GLM-Image model weights +- `transformers` v5.3.0 or above diff --git a/examples/online_serving/glm_image/README.md b/examples/online_serving/glm_image/README.md index 13ed00861..7ba4b501c 100644 --- a/examples/online_serving/glm_image/README.md +++ b/examples/online_serving/glm_image/README.md @@ -196,3 +196,9 @@ gpu_memory_utilization: 0.5 ``` - The first request may be slow due to model warmup. Subsequent requests will be faster. + +- If you encounter `Transformers does not recognize this architecture` error, your have to upgrade `transformers` package to `5.3.0` or above: + +``` +pip install --upgrade transformers +```