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

[V1] v1 engine + full CUDA graph support for PLaMo2 (#23998)

Browse Source 
Signed-off-by: Hemmi Shinichi <shemmi@preferred.jp>
Signed-off-by: nopperl <54780682+nopperl@users.noreply.github.com>
Co-authored-by: Hemmi Shinichi <shemmi@preferred.jp>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>
This commit is contained in:
nopperl
2025-09-04 00:24:02 +09:00
committed by GitHub
parent 6d80ae83e1
commit fa4311d85f
6 changed files with 349 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/usage/v1_guide.md
View File

@@ -110,7 +110,7 @@ Models using selective state-space mechanisms instead of standard transformer at
Models that use Mamba-2 and Mamba-1 layers (e.g., `Mamba2ForCausalLM`, `MambaForCausalLM`,`FalconMambaForCausalLM`) are supported.
Hybrid models that combine Mamba-2 and Mamba-1 layers with standard attention layers are also supported (e.g., `BambaForCausalLM`,
`Zamba2ForCausalLM`, `NemotronHForCausalLM`, `FalconH1ForCausalLM` and `GraniteMoeHybridForCausalLM`, `JambaForCausalLM`).
`Zamba2ForCausalLM`, `NemotronHForCausalLM`, `FalconH1ForCausalLM` and `GraniteMoeHybridForCausalLM`, `JambaForCausalLM`, `Plamo2ForCausalLM`).
Hybrid models with mechanisms different to Mamba are also supported (e.g, `MiniMaxText01ForCausalLM`, `MiniMaxM1ForCausalLM`, `Lfm2ForCausalLM`).