DeepSpeed
Enabled Qwen2-MoE Tensor Parallelism (TP) inference
#6551
Merged
Overview
Commits
5
Changes
View On GitHub

Enabled Qwen2-MoE Tensor Parallelism (TP) inference #6551

loadams merged 5 commits into deepspeedai:master from gyou2021:qwen2-moe
gyou2021
gyou2021 gyou2021 requested a review from awan-10 awan-10 1 year ago
gyou2021 gyou2021 requested a review from arashb arashb 1 year ago
gyou2021 Enabled Qwen2-MoE Tensor Parallism (TP) inference
08f728d3
delock
Yejing-Lai
gyou2021
gyou2021 Merge branch 'master' into qwen2-moe
7cff123c
gyou2021
gyou2021 Changed linear filter of qwen2-moe from _replace_module() to _replace…
97f22ff2
delock
gyou2021
gyou2021 Added Qwen2-MoE to the model list of auto_tp
deebfa0d
delock
loadams
loadams approved these changes on 2024-10-08
loadams Merge branch 'master' into qwen2-moe
932d4b2a
loadams loadams requested a review from tjruwase tjruwase 1 year ago
loadams loadams merged 474a3288 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum