Top repos they contribute to (2)
Ranked by their commits
MTPLXPython2.24x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
2.7k2commits
club-3090PythonCommunity recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1× and 2× cards.
2.5k2commits
Related contributors
People who work on the same repos- noonghunna1shared repo2.3kcommitsclub-3090
- youssofal1shared repo1.8kcommitsMTPLX
- wasifbasharat1shared repo836commitsclub-3090
- davidtai1shared repo143commitsMTPLX
- eddietheengineer1shared repo103commitsclub-3090
- jvmenen1shared repo47commitsMTPLX
- github-actions[bot]1shared repo30commitsclub-3090
- PhilipJohnBasile1shared repo24commitsMTPLX
- paulp831shared repo23commitsclub-3090
- dependabot[bot]1shared repo22commitsMTPLX
- Cyb3rb1ade1shared repo17commitsMTPLX
- stooit1shared repo14commitsMTPLX




