vllm-torchtpu
A high-throughput and memory-efficient inference and serving engine for LLMs
Activity
- Latest release
- 1w ago
- Total releases
- 2
- Cadence
- ~3 days
- Last 12 months
- 2
Details
- License
- Apache-2.0
- First release
- Oct 16, 2026
Releases
| Version | Released | |
|---|---|---|
0.29.0
minor
| ||
0.0.0
initial
|