Repository Issue Activity (beta)

#276 Build error ROCm GPU

#278 Does TurboQuant offer something tiiny can use?

#88 macOS/Metal inference support

#267 Build failure on Linux

#277 ChromeOS compatibility and host computer AI computing capability pooling with Tiiny

#274 Any plan on sharing Pocket Lab's available models on hf?

#270 Support RK series

#124 Would you please kindly offer the data, codes, or settings for training the predictor?

#269 Powerinfer's server-side babble has occurred while the command-side looks good

#268 What will SmallThinker do in the prefill stage?

#264 Incomplete fallback in libaz for CPUs without AVX2

#265 有没有什么办法能够让模型对于中文支持地更好一些？

#263 无法复现smallthinker-4ba0.6b在8elite手机上的性能数据

#228 about the use of OPT model

#85 Fix offloading / VRAM budget bugs

#198 为什么执行过程中没有gpu offload，这边执行的gpu为a100 80G，

#234 How to OPT model with PowerInfer?

#250 Question on GGUF file

#93 Meta: Wider model support for PowerInfer

#257 UBSAN: runtime error: member access within null pointer of type

#256 Integer Overflow Vulnerability in gguf_fread_str()

#194 Source for v2 (mobile inference engine)

#255 Predictor training details

#254 合作咨询

#253 section 6.3.1, computational constraint is not implemented