kacper-daftcode / vLLM-Moet
Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and 2-bit experts on vLLM v0.24.0
Why this job: topics: llm-inference, vllm
What it does
Frontier Mixture-of-Experts models on RTX PRO 6000 and RTX 5090 (sm_120), where the official vLLM images do not run them or the official checkpoints do not fit. The changes are kernel-side patches on official vLLM images, bit-identical to the paths they replace unless a doc says otherwise, each behind a runtime switch.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit yesterday
- Stars
- 570
- +4 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest tag
- v2026.11.03-r23
- Released 6 days ago
- Built with
- Sass
- 53% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 1 merged
- 0 waiting
- Releases
- 1
- 1 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| vllm-project / vllm | 96,588 | today | Apache-2.0 | Mac, Linux |
| autonomous-ai / Personal-AI-Computer | 1,562 | 4 days ago | MIT | No downloads |
| mw00 / project-maya | 2,712 | 2 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Sass 53%
- Python 35%
- Cuda 8%
- C++ 2%
Topics
- blackwell
- cuda
- deepseek
- llm-inference
- moe
- rtx-5090
- rtx-pro-6000
- sass
- sm120
- vllm
Project record
- JobLocal LLMs
- StatusListed
- Commits499
- Forks49
- Watching9
- Stars in 28 days+29
- CreatedJun 15, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026