FlashMLA
Creator not supplied; see original source.
DeepSeek FlashMLA GitHub repo: multi-head latent attention decoding kernels for Hopper GPUs.
- Level
- Not applicable (entity)
- Models
- Category
- Model Training
- Tags
- infrastructure-chips-efficiency, training-systems
- Source date
- date not stated
- Added
- 2026-10-18
- Last verified
- 2026-10-18
- Status
- ok
- Prerequisites
- n/a (entity)
- Subcategory
- training infrastructure
- Region
- unknown
- Original language
- en
- Access
- free
- Resource reuse
- unknown: Not supplied; no reuse grant asserted. Facet definitions
- Verification basis
- Supplier-reported live check; no independent HTTP verification by this site.
- Access evidence
- Supplier-approved free inventory; not independently verified by this site.
- Source domain
- Infrastructure, chips & efficiency
- Source subdomain
- training systems
- Supplier region label
- China
Summary in our own words. Rights remain with the original creator. Credit and correction policy.