Skip to content

GitLab

Unverified Commit b73e6eb5 authored by Rohan Varma's avatar Rohan Varma Committed by GitHub
Browse files

feat: restructure dsr1 recipes and add gb200 (#3891) 


Signed-off-by: default avatarRohan Varma <rohanv@nvidia.com>
parent e20adb44
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
recipes/deepseek-r1/trtllm/wide_ep/wide_ep_decode.yaml → recipes/deepseek-r1/trtllm/disagg/wide_ep/wide_ep_decode.yaml
View file @ b73e6eb5
......@@ -17,7 +17,7 @@ backend: pytorch
# WideEP related settings
moe_config:
backend: WIDEEP
load_balancer: /mnt/recipes/deepseek-r1/trtllm/wide_ep/eplb.yaml
load_balancer: /mnt/recipes/deepseek-r1/trtllm/disagg/wide_ep/eplb.yaml
# TP/EP/PP/DP
tensor_parallel_size: 16
......
recipes/deepseek-r1/trtllm/wide_ep/wide_ep_prefill.yaml → recipes/deepseek-r1/trtllm/disagg/wide_ep/wide_ep_prefill.yaml
View file @ b73e6eb5
......@@ -17,7 +17,7 @@ backend: pytorch
# WideEP related settings
moe_config:
backend: WIDEEP
load_balancer: /mnt/recipes/deepseek-r1/trtllm/wide_ep/eplb.yaml
load_balancer: /mnt/recipes/deepseek-r1/trtllm/disagg/wide_ep/eplb.yaml
# TP/EP/PP/DP
tensor_parallel_size: 16
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment