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

Update docs for Minimax-Text support (#22562)

Browse Source 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
This commit is contained in:
Thomas Parnell
2025-08-09 09:18:18 +02:00
committed by GitHub
parent 0edc0cd52b
commit 2be07a0db1
2 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/usage/v1_guide.md
View File

@ -111,6 +111,10 @@ Models that combine Mamba-2 and Mamba-1 layers with standard attention layers ar
`Zamba2ForCausalLM`, `NemotronHForCausalLM`, `FalconH1ForCausalLM` and `GraniteMoeHybridForCausalLM`, `JambaForCausalLM`). Please note that
these models currently require disabling prefix caching and using the FlashInfer attention backend in V1.
Hybrid models with mechanisms different to Mamba are also supported (e.g, `MiniMaxText01ForCausalLM`, `MiniMaxM1ForCausalLM`).
Please note that these models currently require disabling prefix caching, enforcing eager mode, and using the FlashInfer
attention backend in V1.
#### Encoder-Decoder Models
Models requiring cross-attention between separate encoder and decoder (e.g., `BartForConditionalGeneration`, `MllamaForConditionalGeneration`)