gemma.cpp/io
Jan Wassenberg cb188d4a0e Fix RowT issue and improve Griffin (currently still broken)
Use type-safe MatPtrT via dynamic_cast, avoid/remove unsafe RowT
activations: Griffin tensors are now padded
Griffin: add batching support, fix conv1d_cache allocation
weights: bundle to TensorToRead, add kNoPad flag, fix SplitW1
const-correct fix for ForEachTensor
blob_store: move BlobIO2 to .cc and rename BlobIO
PiperOrigin-RevId: 760610094
2025-05-19 07:02:10 -07:00
..
BUILD.bazel Move fields, io* and blob* from compression/ into io/ 2025-05-06 11:17:19 -07:00
blob_compare.cc 3.8x speedup of weights loading via preadv on Linux 2025-05-15 11:55:15 -07:00
blob_store.cc Fix RowT issue and improve Griffin (currently still broken) 2025-05-19 07:02:10 -07:00
blob_store.h Fix RowT issue and improve Griffin (currently still broken) 2025-05-19 07:02:10 -07:00
blob_store_test.cc 3.8x speedup of weights loading via preadv on Linux 2025-05-15 11:55:15 -07:00
fields.cc Move fields, io* and blob* from compression/ into io/ 2025-05-06 11:17:19 -07:00
fields.h Move fields, io* and blob* from compression/ into io/ 2025-05-06 11:17:19 -07:00
fields_test.cc Move fields, io* and blob* from compression/ into io/ 2025-05-06 11:17:19 -07:00
io.cc 3.8x speedup of weights loading via preadv on Linux 2025-05-15 11:55:15 -07:00
io.h 3.8x speedup of weights loading via preadv on Linux 2025-05-15 11:55:15 -07:00
io_win.cc Cleanup: remove unused kCyclic, remove 2 suffix 2025-05-13 01:06:41 -07:00
migrate_weights.cc Move fields, io* and blob* from compression/ into io/ 2025-05-06 11:17:19 -07:00