zipenghao/strata-v100-sm70

Unofficial third-party patches: run Strata (Qwen3.8-Flash-Next) on 2x Tesla V100 sm_70 - platform patches, a PLE correctness fix that garbles output if unpatched, dual-GPU tuning to 43 tok/s @128K

语言：Shell · GitHub 星标：9 · Fork：0

话题：cuda · gguf · linux · llm-inference · moe · patches · qwen3-next · sm-70

在 GitHub 上查看原仓库