kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-16 15:55:08 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][chore] AutoDeploy: Set nanov3 and superv3 configs to use flashinfer ssm (#11183)

Browse Source 
Signed-off-by: Gal Hubara Agam <96368689+galagam@users.noreply.github.com>
This commit is contained in:
Gal Hubara-Agam 2026-02-04 19:46:15 +02:00 committed by GitHub
parent d90a8e5700
commit 767b8dcab3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/auto_deploy/nano_v3.yaml
View File

@ -45,3 +45,5 @@ transforms:
fuse_mamba_a_log:
stage: post_load_fusion
enabled: true
insert_cached_ssm_attention:
backend: flashinfer_ssm

2
examples/auto_deploy/super_v3.yaml
View File

@ -44,3 +44,5 @@ transforms:
fuse_mamba_a_log:
stage: post_load_fusion
enabled: true
insert_cached_ssm_attention:
backend: flashinfer_ssm