Skip to content

Commit b7858c2

Browse files
authored
【Update Docs】update supported_models doc (#2836)
* update supported_models doc
1 parent 09bbac6 commit b7858c2

File tree

2 files changed

+2
-2
lines changed

2 files changed

+2
-2
lines changed

docs/supported_models.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -14,11 +14,11 @@ export FD_MODEL_CACHE=/ssd1/download_models
1414

1515
| Model Name | Context Length | Quantization | Minimum Deployment Resources | Notes |
1616
| :------------------------------------------ | :------------- | :----------- | :--------------------------- | :----------------------------------------------------------------------------------------- |
17-
| baidu/ERNIE-4.5-VL-424B-A47B-Paddle | 32K/128K | WINT2 | 1*141G GPU VRAM/1T RAM | Chunked Prefill required for 128K |
1817
| baidu/ERNIE-4.5-VL-424B-A47B-Paddle | 32K/128K | WINT4 | 4*80G GPU VRAM/1T RAM | Chunked Prefill required for 128K |
1918
| baidu/ERNIE-4.5-VL-424B-A47B-Paddle | 32K/128K | WINT8 | 8*80G GPU VRAM/1T RAM | Chunked Prefill required for 128K |
2019
| baidu/ERNIE-4.5-300B-A47B-Paddle | 32K/128K | WINT4 | 4*64G GPU VRAM/600G RAM | Chunked Prefill required for 128K |
2120
| baidu/ERNIE-4.5-300B-A47B-Paddle | 32K/128K | WINT8 | 8*64G GPU VRAM/600G RAM | Chunked Prefill required for 128K |
21+
| baidu/ERNIE-4.5-300B-A47B-2Bits-Paddle | 32K/128K | WINT2 | 1*141G GPU VRAM/600G RAM | Chunked Prefill required for 128K |
2222
| baidu/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle | 32K/128K | W4A8C8 | 4*64G GPU VRAM/160G RAM | Fixed 4-GPU setup, Chunked Prefill recommended |
2323
| baidu/ERNIE-4.5-300B-A47B-FP8-Paddle | 32K/128K | FP8 | 8*64G GPU VRAM/600G RAM | Chunked Prefill recommended, only supports PD Disaggragated Deployment with EP parallelism |
2424
| baidu/ERNIE-4.5-300B-A47B-Base-Paddle | 32K/128K | WINT4 | 4*64G GPU VRAM/600G RAM | Chunked Prefill recommended |

docs/zh/supported_models.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -14,11 +14,11 @@ export FD_MODEL_CACHE=/ssd1/download_models
1414

1515
| 模型名 | 上下文长度 | 量化方式 | 最小部署资源 | 说明 |
1616
| :------------------------------------------ | :--------- | :------- | :-------------------- | :---------------------------------------------- |
17-
| baidu/ERNIE-4.5-VL-424B-A47B-Paddle | 32K/128K | WINT2 | 1卡*141G显存/1T内存 | 128K需要开启Chunked Prefill |
1817
| baidu/ERNIE-4.5-VL-424B-A47B-Paddle | 32K/128K | WINT4 | 4卡*80G显存/1T内存 | 128K需要开启Chunked Prefill |
1918
| baidu/ERNIE-4.5-VL-424B-A47B-Paddle | 32K/128K | WINT8 | 8卡*80G显存/1T内存 | 128K需要开启Chunked Prefill |
2019
| baidu/ERNIE-4.5-300B-A47B-Paddle | 32K/128K | WINT4 | 4卡*64G显存/600G内存 | 128K需要开启Chunked Prefill |
2120
| baidu/ERNIE-4.5-300B-A47B-Paddle | 32K/128K | WINT8 | 8卡*64G显存/600G内存 | 128K需要开启Chunked Prefill |
21+
| baidu/ERNIE-4.5-300B-A47B-2Bits-Paddle | 32K/128K | WINT2 | 1卡*141G显存/600G内存 | 128K需要开启Chunked Prefill |
2222
| baidu/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle | 32K/128K | W4A8C8 | 4卡*64G显存/160G内存 | 限定4卡,建议开启Chunked Prefill |
2323
| baidu/ERNIE-4.5-300B-A47B-FP8-Paddle | 32K/128K | FP8 | 8卡*64G显存/600G内存 | 建议开启Chunked Prefill,仅在PD分离EP并行下支持 |
2424
| baidu/ERNIE-4.5-300B-A47B-Base-Paddle | 32K/128K | WINT4 | 4卡*64G显存/600G内存 | 建议开启Chunked Prefill |

0 commit comments

Comments
 (0)