turbo-attn
Optimized CUDAgraph-enabled kernels and attention backend for vLLM, SGLang and more based on TurboQuant near-lossless KV cache compression.
Activity
- Latest release
- 4d ago
- Total releases
- 141
- Cadence
- ~daily
- Last 12 months
- 141
Details
- License
- Apache-2.0
- First release
- Apr 30, 2026
Releases
| Version | Released | |
|---|---|---|
0.55.2
patch
| ||
0.55.1
patch
| ||
0.55.0
minor
| ||
0.54.0
minor
| ||
0.53.0
minor
| ||
0.52.0
minor
| ||
0.51.0
minor
| ||
0.50.0
minor
| ||
0.49.0
minor
| ||
0.48.0
minor
| ||
0.47.0
minor
| ||
0.46.0
minor
| ||
0.44.0
minor
| ||
0.43.1
patch
| ||
0.43.0
minor
| ||
0.42.0
minor
| ||
0.41.2
patch
| ||
0.41.1
patch
| ||
0.41.0
minor
| ||
0.40.1
patch
| ||
0.40.0
minor
| ||
0.39.0
minor
| ||
0.38.6
patch
| ||
0.38.5
patch
| ||
0.38.4
patch
| ||
0.38.3
patch
| ||
0.38.2
patch
| ||
0.38.1
patch
| ||
0.38.0
minor
| ||
0.37.8
patch
| ||
0.37.7
patch
| ||
0.37.6
patch
| ||
0.37.5
patch
| ||
0.37.4
patch
| ||
0.37.3
patch
| ||
0.37.2
patch
| ||
0.37.1
patch
| ||
0.37.0
minor
| ||
0.36.1
patch
| ||
0.36.0
minor
| ||
0.35.4
patch
| ||
0.35.3
patch
| ||
0.35.2
patch
| ||
0.35.1
patch
| ||
0.35.0
minor
| ||
0.34.0
minor
| ||
0.33.3
patch
| ||
0.33.2
patch
| ||
0.33.1
patch
| ||
0.33.0
minor
|
1–50 of 141