A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 9, 10:00 UTC
[Bugfix] Fix broken GLM-OCR initialization (#33350)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Isotr0py committed
Jan 29, 2026 at 23:56 UTC
5e73e4900c803253d84496b2eadad5be3b387aae
1 file changed
+1
-1
vllm/model_executor/models/glm_ocr.py
+1
-1
@@ -249,7 +249,7 @@ class GlmOcrPatchMerger(Glm4vPatchMerger):
249
class GlmOcrVisionTransformer(Glm4vVisionTransformer):
250
def __init__(
251
self,
252
- vision_config: GlmOcrVisionConfig,
252
+ vision_config: "GlmOcrVisionConfig",
253
norm_eps: float = 1e-5,
254
quant_config: QuantizationConfig | None = None,
255
prefix: str = "",