kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[#8921][chore] AutoDeploy NanoV3 to use SYMM_MEM allreduce strategy (#9797)

Browse Source 
Signed-off-by: Eran Geva <19514940+MrGeva@users.noreply.github.com>
This commit is contained in:
Eran Geva 2025-12-09 23:05:38 +02:00 committed by GitHub
parent 7d7d05d8db
commit 4da3121363
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/auto_deploy/nano_v3.yaml
View File

@ -13,8 +13,8 @@ kv_cache_config:
enable_block_reuse: false
transforms:
detect_sharding:
allreduce_strategy: SYMM_MEM
sharding_dims: ['ep', 'bmm']
allreduce_strategy: 'AUTO'
manual_config:
head_dim: 128
tp_plan: