dfloat11
DFloat11: Fast and memory-efficient GPU inference for losslessly compressed LLMs and diffusion models
Activity
- Latest release
- 1y ago
- Total releases
- 6
- Cadence
- ~16 days
- Last 12 months
- 0
Details
- First release
- Apr 17, 2025
| Version | Released | |
|---|---|---|
0.5.0
minor
|
0.5.0
minor
Dependencies (8)
|
|
0.3.2
patch
|
0.3.2
patch
Dependencies (6)
|
|
0.3.1
patch
|
0.3.1
patch
Dependencies (6)
|
|
0.3.0
minor
|
0.3.0
minor
Dependencies (6)
|
|
0.2.0
minor
|
0.2.0
minor
Dependencies (6)
|
|
0.1.0
initial
|
0.1.0
initial
Dependencies (5)
|