Skip to content

Navigation Menu

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

ROCm / vllm Public

forked from vllm-project/vllm

Notifications You must be signed in to change notification settings
Fork 28
Star 53

Code
Issues 1
Pull requests 16
Actions
Projects
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Actions
Projects
Security
Insights

Ingest FP8 attn scales and use them in ROCm FlashAttention#338

Merged

gshtras merged 7 commits intomainROCm/vllm:mainfrom ingest_fp8_attn_scalesROCm/vllm:ingest_fp8_attn_scalesCopy head branch name to clipboard

Dec 20, 2024

+157-81

Conversation Commits7 (7)Checks Files changed

Commits

Commits on Dec 19, 2024

Ingest FP8 attn scales and use them in Triton FA, if present
mawong-amd
committed
Disabling calc_kv_scales if the checkoint has them. Enabling fp8 attention for dynamic quantization
gshtras
committed
q_range as an env
gshtras
committed
format
gshtras
committed
Dedupe FA/PA attn toggles, set FA off by default
mawong-amd
committed
Lint again, to fixed point
mawong-amd
committed
Don't calculate KV scales dynamically if Q scale is included
mawong-amd
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.