biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[New Model]: google/embeddinggemma-300m (#24318)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
This commit is contained in:
wang.yuqi
2025-09-06 13:58:36 +08:00
committed by GitHub
parent 53b19ccdd5
commit 6d6c6b05d3
9 changed files with 73 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config/__init__.py
View File

@@ -2750,6 +2750,8 @@ _STR_DTYPE_TO_TORCH_DTYPE = {
_FLOAT16_NOT_SUPPORTED_MODELS = {
"gemma2": "Numerical instability. Please use bfloat16 or float32 instead.",
"gemma3": "Numerical instability. Please use bfloat16 or float32 instead.",
"gemma3_text":
"Numerical instability. Please use bfloat16 or float32 instead.",
"plamo2": "Numerical instability. Please use bfloat16 or float32 instead.",
"glm4": "Numerical instability. Please use bfloat16 or float32 instead.",
}