Compare repositories
This page shows the Star History and the facts of 2 to 5 repositories in the Repository Index, side by side. You choose the repositories. The page does not rank them.
Facts
| Fact | syv-ai/HyperQwen Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks. | StartLuxLabs/StartLux-Prism Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers. |
|---|---|---|
| Stars | 2,567 | 298 |
| Net stars, last 30 days | +694 | Not recorded |
| Largest star day | +128 on Aug 25, 2026 | +38 on Oct 23, 2026 |
| Milestone reached in the record | 1,000 on Sep 1, 2026 | 100 on Oct 27, 2026 |
| Forks | 325 | 5 |
| Language | Python | Python |
| License | APACHE-2.0 | No license |
| Created | Aug 15, 2026 | Oct 13, 2026 |
| Last push | Nov 3, 2026 | Oct 27, 2026 |
| Archived | No | No |
| Health facts: Maintenance | 3 of 4 checks | 3 of 4 checks |
| Health facts: Releases | 0 of 3 checks (1 without data) | 0 of 3 checks (1 without data) |
| Health facts: Security practice | 0 of 1 check | 0 of 1 check |
| Health facts: Community files | 1 of 3 checks | 0 of 3 checks |
| Commits, last 13 weeks | 654 | 28 |
| Weeks with commits, last 52 | 12 of 52 | 1 of 52 |
| In the Repository Index since | Oct 23, 2026 | Oct 28, 2026 |
Topics that all of them have on the Repository Host: llm-inference, quantization, cuda. The facts come from the Repository Host and from the Star History that AwesomeRepos records. A shared topic does not mean that one repository can replace another. Each Health Facts row is one dimension alone. AwesomeRepos does not add them into one score. How each check is defined