PR #1726 Fp8 Support - SemanticDiff

Fp8 Support #1726

Narsil merged 12 commits into main from fp8

Initial fp8.

50d5a3c1

Dummy but working version.

e1e9a184

Updating docs.

be59a6bc

typo removal.

6568e481

Marking the flag as really not the fastest and BETA.

eb40f8cc

Forgot to update docs.

8cd198a6

Update docs2.

c31cb32d

Fp8 support.

b24bdb9f

Narsil commented on 2024-04-11

Update docs/source/basic_tutorials/launcher.md

66195d83

Style.

a352563e

drbh dismissed these changes on 2024-04-11

dongs0104 commented on 2024-04-12

Update server/text_generation_server/utils/layers.py

5ef2a48f

Narsil dismissed their stale review via 5ef2a48f 1 year ago

Narsil commented on 2024-04-12

Update server/text_generation_server/utils/layers.py

666cde0e

Narsil merged 408dbc48 into main 1 year ago

Narsil deleted the fp8 branch 1 year ago

Reviewers

dongs0104

drbh

Assignees

No one assigned

Labels

None yet

Milestone

No milestone