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
- 21h ago
- Total releases
- 171
- Cadence
- ~daily
- Last 12 months
- 171
Details
- License
- Apache-2.0
- First release
- Apr 30, 2026
Releases
| Version | Released | |
|---|---|---|
0.70.2
patch
| ||
0.70.1
patch
| ||
0.70.0
minor
| ||
0.69.1
patch
| ||
0.69.0
minor
| ||
0.68.1
patch
| ||
0.68.0
minor
| ||
0.67.0
minor
| ||
0.66.0
minor
| ||
0.65.0
minor
| ||
0.64.0
minor
| ||
0.63.0
minor
| ||
0.62.3
patch
| ||
0.62.2
patch
| ||
0.62.1
patch
| ||
0.62.0
minor
| ||
0.61.0
minor
| ||
0.60.4
patch
| ||
0.60.3
patch
| ||
0.60.2
patch
| ||
0.60.1
patch
| ||
0.60.0
minor
| ||
0.59.0
minor
| ||
0.58.0
minor
| ||
0.57.2
patch
| ||
0.57.1
patch
| ||
0.57.0
minor
| ||
0.56.2
patch
| ||
0.56.1
patch
| ||
0.56.0
minor
| ||
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
|
1–50 of 171