- In front of my pc
- @Funball2
- https://huggingface.co/halt95
- https://ko-fi.com/halt95
Popular repositories Loading
-
qwen38-flash-next-3090s
qwen38-flash-next-3090s PublicQwen3.8-Flash-Next on 4x RTX 3090 with vLLM: 806,792 kv pool, 160-175tok/s single decode, 3 x 262K sessions resident, MTP, host-mapped PLE, pinned build and container recipes.
Python 12
-
qwen38-27b-3090s
qwen38-27b-3090s PublicQwen3.8-27B at 262K context on dual or quad RTX 3090s: stock vLLM 0.30.0 + 5 patches, FP8 KV pool 794K (dual) / 1.95M (quad), MTP K=3
Python 2
-
Swift1.5-qwen38-flash-next-3090s
Swift1.5-qwen38-flash-next-3090s PublicSwift 1.5 post-train of Qwen3.8-Flash-Next on 4x RTX 3090 with vLLM: W4A16 checkpoint on the unchanged Flash-Next v2.2.0 engine, TP2 x PP2 + EP, 806,792-token FP8 KV pool, 262K context, MTP K=3, re…
Shell 2
-
Z690-pcie-bifurcation-redriver-lock
Z690-pcie-bifurcation-redriver-lock PublicPin bifurcated x8/x8 PCIe links to Gen 4 on an ASUS Z690 that ignores its BIOS speed setting. Unraid User Scripts write LnkCtl2 on endpoint and root port, retrain, then start the VM before firmware…
Shell 1
-
If the problem persists, check the GitHub status page or contact support.