text-generation-inference
[gaudi] Deepseek v2 mla and add ep to unquantized moe
#3287
Merged

[gaudi] Deepseek v2 mla and add ep to unquantized moe #3287

sywangyi
sywangyi applied mla to deepseek v2
433029e5
sywangyi add ep to improve perf
82a9435a
sywangyi
sywangyi sywangyi changed the title Deepseek v2 mla Deepseek v2 mla and add ep to unquantized moe 191 days ago
regisss
regisss approved these changes on 2025-07-07
regisss regisss changed the title Deepseek v2 mla and add ep to unquantized moe [gaudi] Deepseek v2 mla and add ep to unquantized moe 191 days ago
regisss regisss merged ebb26f0c into main 191 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone