DeepSpeed
Add support for Microsoft Phi-3 model to DeepSpeed-FastGen
#5559
Merged

Add support for Microsoft Phi-3 model to DeepSpeed-FastGen #5559

loadams merged 11 commits into master from adk9/phi3-inference
adk9
adk9 Add support for Microsoft Phi-3 model to DeepSpeed-FastGen
eb636acd
adk9 Fix fused GatedMLP to comply with inference v2 format
4bf4b0f2
adk9 Add link to FastGen blog
13260fb1
adk9 Rename Phi to Phi3
e79d4b4d
adk9 adk9 force pushed from 3a678e80 to e79d4b4d 1 year ago
adk9 Fix formatting
cec78ee1
adk9 adk9 marked this pull request as ready for review 1 year ago
adk9 adk9 requested a review from mrwyattii mrwyattii 1 year ago
adk9 adk9 requested a review from awan-10 awan-10 1 year ago
adk9 adk9 requested a review from arashb arashb 1 year ago
adk9 adk9 requested a review from tjruwase tjruwase 1 year ago
adk9 adk9 requested a review from loadams loadams 1 year ago
loadams Merge branch 'master' into adk9/phi3-inference
43010775
adk9 Phi-3 mini has no unmapped param
702bad7e
adk9 adk9 force pushed from 0b59cdb0 to 702bad7e 1 year ago
adk9 adk9 force pushed from dd4868fe to 702bad7e 1 year ago
adk9 Merge branch 'master' into adk9/phi3-inference
24176bdd
adk9 Merge branch 'master' into adk9/phi3-inference
471ac01b
adk9 adk9 removed review request from mrwyattii mrwyattii 1 year ago
adk9 adk9 requested a review from HeyangQin HeyangQin 1 year ago
adk9 Merge branch 'master' into adk9/phi3-inference
8becbba0
HeyangQin
HeyangQin approved these changes on 2024-07-15
loadams Merge branch 'master' into adk9/phi3-inference
8f8b0320
loadams loadams enabled auto-merge 1 year ago
loadams loadams merged 6a163e03 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone