| .. |
|
python
|
Allow conversion, loading and inference with NUQ.
|
2025-02-05 07:45:54 -08:00 |
|
BUILD.bazel
|
Further speed up blob_compare: single alloc, use dual sockets
|
2025-02-09 10:53:49 -08:00 |
|
analyze.h
|
Major compression update, arbitrary-len unpack + new Dot
|
2024-09-10 02:22:19 -07:00 |
|
blob_compare.cc
|
Further speed up blob_compare: single alloc, use dual sockets
|
2025-02-09 10:53:49 -08:00 |
|
blob_store.cc
|
Expose BlobReader::Keys()
|
2024-11-07 10:28:39 -08:00 |
|
blob_store.h
|
Added the TensorInfo arg to the compressor so the shape and scale can be output correctly to the file in future.
|
2024-12-11 01:26:35 -08:00 |
|
blob_store_test.cc
|
Expose BlobReader::Keys()
|
2024-11-07 10:28:39 -08:00 |
|
compress-inl.h
|
Infra improvements (2)
|
2025-01-23 01:55:19 -08:00 |
|
compress.cc
|
Added MatPtr/MatPtrT/MatStorageT/MatStorage as a dynamically-sized replacement for CompressedArray.
|
2024-10-10 08:22:30 -07:00 |
|
compress.h
|
Allow conversion, loading and inference with NUQ.
|
2025-02-05 07:45:54 -08:00 |
|
compress_test.cc
|
Allow conversion, loading and inference with NUQ.
|
2025-02-05 07:45:54 -08:00 |
|
compress_weights.cc
|
Added ability to load/save a complete model file, including tokenizer.
|
2024-12-19 07:59:41 -08:00 |
|
convert_weights.py
|
Cleanup: move util/compress and convert_weights to compression/
|
2024-07-05 04:16:52 -07:00 |
|
distortion.h
|
Refactor/cleanup, remove even_odd
|
2024-09-04 09:25:13 -07:00 |
|
distortion_test.cc
|
Major compression update, arbitrary-len unpack + new Dot
|
2024-09-10 02:22:19 -07:00 |
|
fields.cc
|
Added ability to load/save a complete model file, including tokenizer.
|
2024-12-19 07:59:41 -08:00 |
|
fields.h
|
Windows build fixes: struct vs class, unused arg/var, avoid VLA, Deleter arg, casts
|
2025-02-07 07:38:55 -08:00 |
|
fields_test.cc
|
Added ability to load/save a complete model file, including tokenizer.
|
2024-12-19 07:59:41 -08:00 |
|
io.cc
|
Further improve IO, enable multiple backends without -D.
|
2024-04-19 00:40:29 -07:00 |
|
io.h
|
Major duplicated code reduction in test/benchmarks
|
2024-06-14 00:16:25 -07:00 |
|
io_win.cc
|
Further improve IO, enable multiple backends without -D.
|
2024-04-19 00:40:29 -07:00 |
|
migrate_weights.cc
|
Allow interactive use with new single-file weight format.
|
2025-01-15 07:22:33 -08:00 |
|
nuq-inl.h
|
Fix nuq Enc() to handle groups < kGroupSize.
|
2025-02-10 07:17:59 -08:00 |
|
nuq_test.cc
|
Base interleaved handling for 4.5-bit NUQ, specifically Enc, DecompressAndZeroPad, and Dec2. Includes tests.
|
2025-01-31 10:35:32 -08:00 |
|
sfp-inl.h
|
Major compression update, arbitrary-len unpack + new Dot
|
2024-09-10 02:22:19 -07:00 |
|
sfp_test.cc
|
Major compression update, arbitrary-len unpack + new Dot
|
2024-09-10 02:22:19 -07:00 |
|
shared.h
|
Fix nuq Enc() to handle groups < kGroupSize.
|
2025-02-10 07:17:59 -08:00 |
|
test_util-inl.h
|
Add double-precision dot variant
|
2024-09-26 12:09:10 -07:00 |
953c877658