vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Commit graph

  • a68a1e7ed0
         metal : log more info on error (#6987) b2772 Kevin Gibbons 2024-04-30 02:34:50 -07:00
  • 9c67c2773d
         ggml : add Flash Attention (#5021) b2771 Georgi Gerganov 2024-04-30 12:16:08 +03:00
  • fcc5a5e0fe *.py: fix flake8 warnings brian khuu 2024-04-30 02:36:00 +10:00
  • 5e5e74e3b8 convert-hf-to-gguf.py: print() --> logger brian khuu 2024-04-24 22:50:34 +10:00
  • 2d2bc99385 convert-hf-to-gguf.py: add additional logging brian khuu 2024-04-21 11:33:27 +10:00
  • 58d5a5d2d5 constants.py: logger no longer required brian khuu 2024-04-21 11:28:41 +10:00
  • ad53853a39 python-lint.yml: use .flake8 file instead brian khuu 2024-04-19 09:42:27 +10:00
  • fe1d7f605d gguf-py/gguf/*.py: use __name__ as logger name brian khuu 2024-04-18 16:02:36 +10:00
  • b0b51e7874 *.py: refactor logging.basicConfig() brian khuu 2024-04-18 14:44:29 +10:00
  • 1b7c80072b verify-checksum-models.py: use print() for printing table brian khuu 2024-04-18 14:30:13 +10:00
  • aefd7492a3 convert-hf-to-gguf.py: print --> logger.debug or ValueError() brian khuu 2024-04-18 14:26:36 +10:00
  • 3a55ae4d72 gguf-dump.py: dump_metadata() should print to stdout brian khuu 2024-04-18 14:07:36 +10:00
  • 1b1c2ed80b convert.py: warning goes to stderr and won't hurt the dump output brian khuu 2024-04-18 14:04:46 +10:00
  • 62da83a4b8 reader.py: read_gguf_file() use print() over logging brian khuu 2024-04-18 14:03:23 +10:00
  • 510dea0d12 compare-llama-bench.py: add blank line for readability during missing repo response brian khuu 2024-04-18 13:58:05 +10:00
  • e0372a1b5a verify-checksum-model.py: This is the result of the program, it should be printed to stdout. brian khuu 2024-04-18 13:56:05 +10:00
  • ea449058b6 gguf-convert-endian.py: refactor convert_byteorder() to use tqdm progressbar brian khuu 2024-04-18 13:53:55 +10:00
  • dc798d23d7 *.py: Convert logger error and sys.exit() into a raise exception (for atypical error) brian khuu 2024-04-18 11:13:34 +10:00
  • cf38b4b831 constant.py: logger.error then exit should be a raise exception instead brian khuu 2024-04-18 11:10:57 +10:00
  • dc2bff4059 fixup! *.py: logging basiconfig refactor to use conditional expression brian khuu 2024-04-18 10:01:38 +10:00
  • c2e5abd33d *.py: removed commented out logging brian khuu 2024-04-18 10:00:07 +10:00
  • 1cc38d81af *.py: logging basiconfig refactor to use conditional expression brian khuu 2024-04-18 09:49:20 +10:00
  • 44b058d131 convert-hf-to-gguf.py: print() to logger conversion brian khuu 2024-04-15 11:39:26 +10:00
  • dd8b9774eb pre-commit: add flake8-no-print to flake8 and also update pre-commit version brian khuu 2024-04-10 15:41:41 +10:00
  • 8d855b177c gh-actions: add flake8-no-print to flake8 lint step brian khuu 2024-04-10 15:40:53 +10:00
  • c220e353f3 flake8: update flake8 ignore and exclude to match ci settings brian khuu 2024-04-10 15:40:12 +10:00
  • 9ad587a5ee requirements.txt: remove extra line brian khuu 2024-04-10 15:39:32 +10:00
  • f00454fbd4 *.py: Convert all python scripts to use logging module brian khuu 2024-04-10 15:38:41 +10:00
  • 3670e16e9c convert.py: sys.stderr.write --> logger.error brian khuu 2024-04-09 20:57:28 +10:00
  • e6b9d9179b convert.py: convert extra print() to named logger brian khuu 2024-04-08 21:27:47 +10:00
  • 8008082c2a convert.py: use explicit logger id string brian khuu 2024-04-08 20:52:10 +10:00
  • e8be0c8f73 convert.py: named instance logging brian khuu 2024-04-08 10:19:46 +10:00
  • 88c1e2ff10 convert.py: verbose flag takes priority over dump flag log suppression brian khuu 2024-04-07 01:50:05 +11:00
  • 573dcecda1 convert.py: add python logging instead of print() brian khuu 2024-04-07 00:47:49 +11:00
  • c240ae234c
         ci : fix arg order gg/flash-attn Georgi Gerganov 2024-04-30 11:43:36 +03:00
  • 952d03dbea
         convert : use utf8 encoding (#7000) Georgi Gerganov 2024-04-30 11:05:25 +03:00
  • e180fcd3d5
         metal : fix max nsg Georgi Gerganov 2024-04-30 11:04:32 +03:00
  • dc94e5c03f
         convert : update instructions and warning message Georgi Gerganov 2024-04-30 10:31:27 +03:00
  • 5a91d63d8b
         convert : use utf8 encoding Georgi Gerganov 2024-04-30 10:20:18 +03:00
  • a808370c58 examples : new program to verify gguf tokenizer parameters Anisse Astier 2024-04-29 21:57:07 +02:00
  • 5eea11e241 fix up joshcarp 2024-04-30 00:10:58 -04:00
  • 9858fd1457 Fix SwiGlu2 joshcarp 2024-04-29 23:22:02 -04:00
  • ae0b5ea7ae oops netrunnereve 2024-04-29 22:45:59 -04:00
  • 8916954a82 merge netrunnereve 2024-04-29 22:17:12 -04:00
  • 0084a2a8d7 Checkpoint joshcarp 2024-04-29 20:00:44 -04:00
  • 8843a98c2b
         Improve usability of --model-url & related flags (#6930) b2769 Olivier Chafik 2024-04-30 00:52:50 +01:00
  • 0ea4873895 attempting to add stanford changes Steven Prichard 2024-04-29 18:02:43 -05:00
  • 7c3c3eb256 Add comment joshcarp 2024-04-29 17:26:54 -04:00
  • b8aec23086 add minicpm chat template youkpan 2024-04-30 04:49:39 +08:00
  • 8dddc8cc44
         Merge c010ce5274 into b8c1476e44 Tevin Wang 2024-04-29 16:41:01 -04:00
  • 5598a6a87d curl: update failed test (model file collision) + gitignore *.gguf.json Olivier Chafik 2024-04-29 21:13:29 +01:00
  • 68f0a1d0f9 log more info when metal fails Kevin Gibbons 2024-04-29 12:49:31 -07:00
  • b8c1476e44
         Extending grammar integration tests (#6644) b2768 Clint Herron 2024-04-29 14:40:14 -04:00
  • 54fa2e5b23 Unicode symbol modifications to hopefully make log easier to parse visually. Clint Herron 2024-04-29 14:38:06 -04:00
  • 5ba2143c3c Add nop feedforward length joshcarp 2024-04-29 14:32:10 -04:00
  • b712ae4047 Cleaning up forgotten symbols. Modifying simple test to use test harness. Added comments for more verbose descriptions of what each test is accomplishing. Clint Herron 2024-04-29 14:29:42 -04:00
  • 84b966dd7a Merge remote-tracking branch 'origin/master' into model-args Olivier Chafik 2024-04-29 19:25:56 +01:00
  • 6e89d82269 Attempt at OpenElm joshcarp 2024-04-29 14:24:59 -04:00
  • 7fe2fb3fed Implementing suggestions from @ochafik -- grammars and test strings now print and flush before tests to aid in debugging segfaults and whatnot. Clint Herron 2024-04-29 14:17:59 -04:00
  • a273de3c5a Removing trailing whitespace. Clint Herron 2024-04-27 09:47:54 -04:00
  • e3218de5a5 Adding quotes around strings to explicitly show whitespace Clint Herron 2024-04-27 09:45:53 -04:00
  • b7f24dba00 Separating test calls to give more helpful stack traces on failure. Adding verbose messages to give visibility for what is being tested. Clint Herron 2024-04-27 09:38:45 -04:00
  • 7b04c215eb Fixing build when C++17 is not present. Clint Herron 2024-04-12 22:04:45 -04:00
  • 8f17815ca8 Add slightly more complex grammar with quantifiers to test references with quantifiers. Clint Herron 2024-04-12 16:49:05 -04:00
  • ab606c030f Add tests around quantifiers to ensure both matching and non-matching compliance. Clint Herron 2024-04-12 16:35:10 -04:00
  • 9cd07c2f9d Cleaning up integration tests to share code between tests and make it simpler to add new tests. Clint Herron 2024-04-12 16:17:07 -04:00
  • 5539e6fdd1
         main : fix typo in comment in main.cpp (#6985) b2767 Daniel Bevenius 2024-04-29 19:56:59 +02:00
  • ab5f0a7c9d
         main : fix typo in comment in main.cpp Daniel Bevenius 2024-04-29 19:52:35 +02:00
  • 1d8fcc06ba GPT2 custom regex split jaime-m-p 2024-04-29 19:13:18 +02:00
  • 5c38f6ed7a Move unused variable value jaime-m-p 2024-04-29 19:11:37 +02:00
  • b6fafd1747 llama : remove useless return value for some llama_cache_* functions Francis Couture-Harpin 2024-04-29 12:59:43 -04:00
  • b8a7a5a90f
         build(cmake): simplify instructions (cmake -B build && cmake --build build ...) (#6964) b2766 Olivier Chafik 2024-04-29 17:02:45 +01:00
  • 7fc6deadfb build: reword debug instructions around single/multi config split Olivier Chafik 2024-04-29 16:57:03 +01:00
  • 42f9b79811 build: nit / remove -H from cmake example Olivier Chafik 2024-04-29 16:50:27 +01:00
  • ca0275ceb7
         Merge branch 'master' into gg/flash-attn Georgi Gerganov 2024-04-29 18:37:04 +03:00
  • d2c898f746
         ci : tmp disable gguf-split (#6983) Georgi Gerganov 2024-04-29 18:36:39 +03:00
  • 5ddad95e5c
         ci : tmp disable gguf-split gg/tmp-ci Georgi Gerganov 2024-04-29 18:29:38 +03:00
  • 4b39329431 build: revert more --config Release Olivier Chafik 2024-04-29 16:22:36 +01:00
  • cbf99fcf3b build: reinstate --config Release as not the default w/ some generators + document how to build Debug Olivier Chafik 2024-04-29 16:00:29 +01:00
  • 544f1f10ad
         ggml : fix __MSC_VER -> _MSC_VER (#6977) b2764 Georgi Gerganov 2024-04-29 17:55:02 +03:00
  • ffe666572f
         llava-cli : multiple images (#6969) b2763 cpumaxx 2024-04-29 07:34:24 -07:00
  • 2ff76f2458 move ndk code to a new library Elton Kola 2024-04-27 19:21:59 -04:00
  • c460ff1a1c Merge branch 'master' into compilade/refactor-kv-cache Francis Couture-Harpin 2024-04-29 10:31:39 -04:00
  • a09db95eab llama : rename many llama_kv_cache_* functions Francis Couture-Harpin 2024-04-29 10:24:45 -04:00
  • a1616e9f72
         Merge branch 'master' into gg/flash-attn Georgi Gerganov 2024-04-29 17:19:25 +03:00
  • 24affa7db3
         readme : update hot topics Georgi Gerganov 2024-04-29 17:06:19 +03:00
  • b66cdd1c24 Merge remote-tracking branch 'upstream/gg/bpe-preprocess' into gg/bpe-preprocess jaime-m-p 2024-04-29 16:01:07 +02:00
  • f4ab2a4147
         llama : fix BPE pre-tokenization (#6920) b2761 Georgi Gerganov 2024-04-29 16:58:41 +03:00
  • 3f167476b1
         sampling : use std::random_device{}() for default random seed (#6962) b2760 David Renshaw 2024-04-29 09:35:45 -04:00
  • 3055a41805
         convert : fix conversion of some BERT embedding models (#6937) Christian Zhou-Zheng 2024-04-29 09:34:41 -04:00
  • 765cd50afa
         Merge branch 'ggerganov:master' into theme JohnnyB 2024-04-29 14:17:31 +01:00
  • 577277ffd2
         make : change GNU make default CXX from g++ to c++ (#6966) Przemysław Pawełczyk 2024-04-29 15:08:20 +02:00
  • 9c5786161d
         Merge branch 'ggerganov:master' into ag_cuda_graphs agray3 2024-04-29 14:04:11 +01:00
  • bf689c4511
         ggml : fix __MSC_VER -> _MSC_VER Georgi Gerganov 2024-04-29 16:02:19 +03:00
  • ca7f29f568
         ci : add building in MSYS2 environments (Windows) (#6967) b2757 Przemysław Pawełczyk 2024-04-29 14:59:47 +02:00
  • c4f708a93f
         llama : fix typo LAMMAFILE -> LLAMAFILE (#6974) b2756 Johannes Gäßler 2024-04-29 14:36:22 +02:00
  • 80cb3127df
         tests : disable test-tokenizer-1-bpe due to slowness gg/bpe-preprocess Georgi Gerganov 2024-04-29 15:24:39 +03:00
  • 3202676f5d
         llama : more prominent warning for old BPE models Georgi Gerganov 2024-04-29 15:24:27 +03:00
  • 40ad7d7ff2 fix typo: LAMMAFILE -> LLAMAFILE Johannes Gäßler 2024-04-29 14:00:07 +02:00
  • 6d6ce93959
         tests : use faster bpe test Georgi Gerganov 2024-04-29 14:47:25 +03:00