Files
calculet-npu-research-archive/history/llama.cpp/topics/calculet-authored/04-multimodel-capacity.tsv
T

891 B

1ebce9e1a548c2329aa97f53b8b2ad50d968088dce850ff4de25ad1221abc9bf3bb30df252ccd9c362026-05-27T09:38:00+08:00Yunzhe Jiaorigin/runtime_replaceRefactor cal-llm integration by removing runtime capacity loading and adjusting request handling
22716130010c58f1cdd9d94f0e2f8e047bc92dc66b35bda124ccd4ed581dd6088d3ffa4931c2809b62026-05-18T08:40:54+08:00Yunzhe Jiafix n_ctx_slot error by adding runtime capacity loading for cal-llm
31bec0db5a675ddc60fb793be2a746e8f3c8855dc465df20c3e1f3f58d0f5531c796e0941a49c32b02026-04-30T16:02:59+08:00wangbomengorigin/dev-benbench: support 2 calbins
46787a53ab9b4897c5a7b51a4062d7b90e6697d35e1a76abf66178ea85656479a5e19aea7785c09f42026-04-24T09:22:02+08:00wangbomengcalrt:input of multimodel from fp32 to bf16
5059009eeaf20a569abfbac5eb37dad3bb93764281b073661d1311b5300173993b9f31ee7241d86062026-03-10T07:04:22+08:00wangbomengcalrt: add multimodel