0000000000000000000000000000000000000000 048a490f763708b84f186078559c0929ed3fcd9c rurouni <rurouni@debian-ai.local> 1777846613 -0700	clone: from https://github.com/ggml-org/llama.cpp
048a490f763708b84f186078559c0929ed3fcd9c 4d31db4de12113a8901bca66b7d9aa0703a2045d rurouni <rurouni@debian-ai.local> 1783300099 -0700	cherry-pick: ggml : overlap offloaded expert weight uploads with compute
4d31db4de12113a8901bca66b7d9aa0703a2045d f3a1664ea81fb41af41edfd2745defc47acacfa0 rurouni <rurouni@debian-ai.local> 1783300102 -0700	cherry-pick: ggml : size prefetch slots per layer and fix fallback use-after-free
f3a1664ea81fb41af41edfd2745defc47acacfa0 c57607016a1ebdd08d269e3378eee5546fc3bf3a rurouni <rurouni@debian-ai.local> 1783300506 -0700	reset: moving to c576070
c57607016a1ebdd08d269e3378eee5546fc3bf3a 4276dac4a7103a74ead8202fa07dce8f4e5eb958 rurouni <rurouni@debian-ai.local> 1783300507 -0700	cherry-pick: ggml : overlap offloaded expert weight uploads with compute
4276dac4a7103a74ead8202fa07dce8f4e5eb958 c544a27e5a250d8a782edfb6ffc0e2f0e768abc1 rurouni <rurouni@debian-ai.local> 1783300507 -0700	cherry-pick: ggml : size prefetch slots per layer and fix fallback use-after-free