EngineX/xc-llm-kunlun
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[Feature] Support glmx (#194)

Browse Source 
Signed-off-by: Li Wei <liwei.109@outlook.com>
Co-authored-by: tangshiwen <tangshiwen@baidu.com>
Co-authored-by: Xinyu Dong <dongxinyu03@baidu.com>
This commit is contained in:
Li Wei
2026-02-12 15:40:42 +08:00
committed by GitHub
parent 070bfa4a73
commit 744719587e
9 changed files with 159 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
vllm_kunlun/transformer_utils/__init__.py Normal file
View File

27
vllm_kunlun/transformer_utils/config.py Normal file
View File

@@ -0,0 +1,27 @@
from transformers import PretrainedConfig
from vllm.transformers_utils.config import LazyConfigDict, _CONFIG_REGISTRY
_XPU_CONFIG_REGISTRY: dict[str, type[PretrainedConfig]] = LazyConfigDict(
chatglm="ChatGLMConfig",
deepseek_vl_v2="DeepseekVLV2Config",
deepseek_v3="DeepseekV3Config",
deepseek_v32="DeepseekV3Config",
glm_moe_dsa="DeepseekV3Config",
kimi_vl="KimiVLConfig",
Llama_Nemotron_Nano_VL="Nemotron_Nano_VL_Config",
RefinedWeb="RWConfig", # For tiiuae/falcon-40b(-instruct)
RefinedWebModel="RWConfig", # For tiiuae/falcon-7b(-instruct)
jais="JAISConfig",
mlp_speculator="MLPSpeculatorConfig",
medusa="MedusaConfig",
midashenglm="MiDashengLMConfig",
eagle="EAGLEConfig",
speculators="SpeculatorsConfig",
nemotron="NemotronConfig",
olmo3="Olmo3Config",
ovis="OvisConfig",
ultravox="UltravoxConfig",
step3_vl="Step3VLConfig",
step3_text="Step3TextConfig",
qwen3_next="Qwen3NextConfig",
)