chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[GLM-4.6V] Support Pipeline Parallelism for GLM-4.6V & GLM-4.1V (#14720)

Browse Source 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
This commit is contained in:
Yuan Luo
2025-12-10 16:40:12 +08:00
committed by GitHub
parent 87dbdddc93
commit 03836d85d2
4 changed files with 66 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
python/sglang/test/test_utils.py
View File

@@ -57,6 +57,9 @@ DEFAULT_MLA_FP8_MODEL_NAME_FOR_TEST = "neuralmagic/DeepSeek-Coder-V2-Lite-Instru
DEFAULT_MODEL_NAME_FOR_TEST_MLA = "lmsys/sglang-ci-dsv3-test"
DEFAULT_MODEL_NAME_FOR_TEST_MLA_NEXTN = "lmsys/sglang-ci-dsv3-test-NextN"
# VL test models
DEFAULT_MODEL_NAME_FOR_TEST_GLM_41V_PP = "zai-org/GLM-4.1V-9B-Thinking"
# NVFP4 models
DEFAULT_DEEPSEEK_NVFP4_MODEL_FOR_TEST = "nvidia/DeepSeek-V3-0324-FP4"
DEFAULT_MODEL_NAME_FOR_TEST_MOE_NVFP4 = "nvidia/Qwen3-30B-A3B-FP4"