invergent-ai / surogate
Train and serve LLMs at extreme speed and massive throughput.
Why this job: matched by what the repo talks about: llm, throughput, spe, train
What it does
From your first fine-tune to hundreds of concurrent requests.
Get started
curl -LsSf https://github.com/invergent-ai/surogate/releases/latest/download/install.sh | bash
source .venv/bin/activate - Maintenance
- Active
- Last commit 7 days ago
- Stars
- 887
- +3 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- Linux
- From the latest release
- Latest version
- v1.5.15
- Released 7 days ago
- Built with
- C++
- 56% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 98% closed
- 2 still open
- Pull requests
- 210 merged
- 2 waiting
- Releases
- 73
- 30+ in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| unslothai / unsloth | 79,340 | today | Apache-2.0 | Mac, Windows, Linux |
| vllm-project / vllm | 96,774 | today | Apache-2.0 | Mac, Linux |
| sgl-project / sglang | 38,767 | today | Apache-2.0 | No downloads |
More: download files, languages, topics and project record
Languages
- C++ 56%
- Python 23%
- Cuda 19%
- TypeScript 1%
Topics
- cuda
- deep-learning
- fine-tuning
- generative-ai
- llama
- llm
- llms
- nvidia-gpu
- qwen
- sft
Project record
- JobLocal LLMs
- StatusListed
- Commits2,697
- Forks15
- Watching4
- Stars in 28 days+32
- CreatedJan 2, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026