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

[New Model]mBART model (#22883)

Browse Source 
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
This commit is contained in:
汪志鹏
2025-08-16 20:16:58 +08:00
committed by GitHub
parent 4dff91c93d
commit 829bbd7882
6 changed files with 717 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/models/supported_models.md
View File

@@ -330,6 +330,7 @@ th {
| `BambaForCausalLM` | Bamba | `ibm-ai-platform/Bamba-9B-fp8`, `ibm-ai-platform/Bamba-9B` | ✅︎ | ✅︎ | ✅︎ |
| `BloomForCausalLM` | BLOOM, BLOOMZ, BLOOMChat | `bigscience/bloom`, `bigscience/bloomz`, etc. | | ✅︎ | |
| `BartForConditionalGeneration` | BART | `facebook/bart-base`, `facebook/bart-large-cnn`, etc. | | | |
| `MBartForConditionalGeneration` | mBART | `facebook/mbart-large-en-ro`, `facebook/mbart-large-50`, etc. | | | |
| `ChatGLMModel`, `ChatGLMForConditionalGeneration` | ChatGLM | `zai-org/chatglm2-6b`, `zai-org/chatglm3-6b`, `ShieldLM-6B-chatglm3`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `CohereForCausalLM`, `Cohere2ForCausalLM` | Command-R | `CohereLabs/c4ai-command-r-v01`, `CohereLabs/c4ai-command-r7b-12-2024`, etc. | ✅︎ | ✅︎ | ✅︎ |
| `DbrxForCausalLM` | DBRX | `databricks/dbrx-base`, `databricks/dbrx-instruct`, etc. | | ✅︎ | ✅︎ |
@@ -418,6 +419,9 @@ Some models are supported only via the [Transformers backend](#transformers). Th
!!! note
Currently, the ROCm version of vLLM supports Mistral and Mixtral only for context lengths up to 4096.
!!! note
Some mBART models' config files do not have an `architecture` defined. Therefore, you need to use `--hf-overrides '{"architectures": ["MBartForConditionalGeneration"]}'` to explicitly specify the use of the `MBartForConditionalGeneration` architecture.
### Pooling Models
See [this page](./pooling_models.md) for more information on how to use pooling models.