Skip to content

Commit 39ed715

Browse files
Update supported models
1 parent 16b0b51 commit 39ed715

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -67,7 +67,7 @@ Learn how to use FastDeploy through our documentation:
6767
| Model | Data Type | PD Disaggregation | Chunked Prefill | Prefix Caching | MTP | CUDA Graph | Maximum Context Length |
6868
|:--- | :------- | :---------- | :-------- | :-------- | :----- | :----- | :----- |
6969
|ERNIE-4.5-300B-A47B | BF16/WINT4/WINT8/W4A8C8/WINT2/FP8 | ✅(WINT4/W4A8C8/Expert Parallelism)|||✅(WINT4)| WIP |128K |
70-
|ERNIE-4.5-300B-A47B-Base| BF16/WINT4/WINT8 | ✅(WINT4/Expert Parallelism)|||✅(WINT4)| | 128K |
70+
|ERNIE-4.5-300B-A47B-Base| BF16/WINT4/WINT8 | ✅(WINT4/Expert Parallelism)|||✅(WINT4)| WIP | 128K |
7171
|ERNIE-4.5-VL-424B-A47B | BF16/WINT4/WINT8 | WIP || WIP || WIP |128K |
7272
|ERNIE-4.5-VL-28B-A3B | BF16/WINT4/WINT8 ||| WIP || WIP |128K |
7373
|ERNIE-4.5-21B-A3B | BF16/WINT4/WINT8/FP8 |||| WIP ||128K |

0 commit comments

Comments
 (0)