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

Commit graph

  • 563cdc391d
         Support calling mlock() on loaded model data on Linux and macOS (#453) comex 2023-03-24 08:19:05 -07:00
  • 53a941c1e5
         Update llama.cpp Georgi Gerganov 2023-03-24 17:17:56 +02:00
  • a65f23342d
         Merge branch 'master' into mlock Georgi Gerganov 2023-03-24 17:15:24 +02:00
  • 8d4a855c24
         Add embedding mode with arg flag. Currently working (#282) master-8d4a855 Luciano 2023-03-24 08:05:13 -07:00
  • 8e383f1895 gitignore Concedo 2023-03-24 23:02:25 +08:00
  • 1c78ffb964
         Update README.md LostRuins 2023-03-24 22:45:54 +08:00
  • e791827973 added a GUI for selection of models if none was passed in through command line. Concedo 2023-03-24 22:03:57 +08:00
  • c6c60332a4 Optimizations Concedo 2023-03-24 21:33:53 +08:00
  • 3879d84400 Merge branch 'master' into concedo Concedo 2023-03-24 19:28:27 +08:00
  • 706e19e9b4 added ability to fast forward in time through partially duplicated prompts Concedo 2023-03-24 18:50:16 +08:00
  • 8b4b1e1fb3
         Merge branch 'ggerganov:master' into fix-instruct rabidcopy 2023-03-24 03:09:53 -05:00
  • b6b268d441
         Add link to Roadmap discussion Georgi Gerganov 2023-03-24 09:13:35 +02:00
  • 3cd8dde0d1 Revert "Fix memory allocation issues and seg faults" master-3cd8dde Georgi Gerganov 2023-03-24 06:22:28 +02:00
  • a34ba06b38
         Prevent users from using the instruct mode and interactive mode at the same time. mmyjona 2023-03-24 12:19:37 +08:00
  • 2a6daccc40 additional optimizations for POWER9 Cameron Kaiser 2023-03-23 20:23:45 -07:00
  • 34e8e4feef Support calling mlock() on loaded model data on Linux and macOS comex 2023-03-23 20:08:13 -07:00
  • 57dc4dc68a Revert "Fix memory allocation issues and seg faults" Gary Linscott 2023-03-23 18:44:48 -07:00
  • acc36eb0b5 Add AVX2 implementation of ggml_compute_forward_rms_norm_f32 Slaren 2023-03-24 01:10:46 +01:00
  • 9179d089a2 Merge remote-tracking branch 'origin/master' into batch_perplexity Gary Linscott 2023-03-23 18:35:22 -07:00
  • 6041736d6b
         Update README.md Kevin Kwok 2023-03-23 16:00:10 -07:00
  • b64067704e
         fix instruct mode rabidcopy 2023-03-23 17:56:16 -05:00
  • 3e481d05f0
         Update README.md Kevin Kwok 2023-03-23 15:51:16 -07:00
  • f7de57fd3a
         Update README.md Gary Mulder 2023-03-23 22:29:52 +00:00
  • 4870e455b3
         Fix memory allocation issues and seg faults master-4870e45 Georgi Gerganov 2023-03-24 00:11:53 +02:00
  • 483bab2e3d
         Avoid the transposed X branch in the Z = X * Y matrix multiplication (#439) master-483bab2 Georgi Gerganov 2023-03-23 23:22:01 +02:00
  • 5dd94f70b2
         cmake: make sanitizers link Green Sky 2023-03-23 21:46:04 +01:00
  • 2d262ea9f0
         fix perplexity - it's memory needs dont grow, so we skip it Green Sky 2023-03-23 20:50:09 +01:00
  • 404e1da38e
         Fix quantize script not finding models in parent directory (#428) Jed Fox 2023-03-23 16:42:52 -04:00
  • 4cc053b6d5
         Remove oboslete command from Docker script Georgi Gerganov 2023-03-23 22:39:44 +02:00
  • 0ba5a3a9a5
         Obsolete Georgi Gerganov 2023-03-23 22:32:02 +02:00
  • d782609307
         Delete download-pth.py Jed Fox 2023-03-23 16:31:49 -04:00
  • 2e17dfd80a
         Replace EOS with newline to prevent context/memory being flushed by EOS in interactive mode (#333) master-2e17dfd rabidcopy 2023-03-23 15:22:47 -05:00
  • 4a4718e8ab
         More correct load progress Jed Fox 2023-03-23 16:18:37 -04:00
  • 23035f9ba8
         Use seekg to find file size instead Jed Fox 2023-03-23 16:18:29 -04:00
  • 20a1a4e09c
         Fix GPTQ converter (#423) master-ad072fc Timmy Knight 2023-03-23 10:18:13 -10:00
  • ad072fc5ad
         Generate library with CMake (#430) nusu-github 2023-03-24 05:16:48 +09:00
  • 1f9592baf3
         Renames Jed Fox 2023-03-23 16:15:55 -04:00
  • 347592b365
         Fix comment Georgi Gerganov 2023-03-23 22:13:54 +02:00
  • 8a3c34bb54
         Embeddings extraction support Georgi Gerganov 2023-03-23 22:02:14 +02:00
  • 424281a4fb
         dynamic estimate of required memory usage Green Sky 2023-03-23 19:21:18 +01:00
  • 55b899b8f2
         Update main.cpp rabidcopy 2023-03-23 13:47:18 -05:00
  • d90112a007
         Avoid the transposed X branch in the Z = X * Y matrix multiplication Georgi Gerganov 2023-03-23 20:40:16 +02:00
  • d6aa749ccf
         Swap from exclusions to allowlist Jed Fox 2023-03-23 13:58:47 -04:00
  • ea10d3ded2
         Command line args bounds checking (#424) master-ea10d3d anzz1 2023-03-23 19:54:28 +02:00
  • ab02a2441c
         Move llama_progress_handler into llama_context_params Jed Fox 2023-03-23 13:36:43 -04:00
  • e47924fd4b
         File load progress reporting Jed Fox 2023-03-22 13:13:29 -04:00
  • 927bc26e03
         Add a Package.swift for SwiftPM support Jed Fox 2023-03-22 10:05:33 -04:00
  • a18c19259a Fix Nix build Ben Siraphob 2023-03-22 00:37:02 -05:00
  • af5ec1ba63
         Fix Nix build Ben Siraphob 2023-03-22 00:37:02 -05:00
  • 1166fda943 Merge branch 'master' into concedo Concedo 2023-03-23 23:51:07 +08:00
  • bfcb4e7c92
         Turn ON PIC when BUILD_SHARED_LIBS is ON nusu-github 2023-03-24 00:23:54 +09:00
  • a50e39c6fe
         Revert "Delete SHA256SUMS for now" (#429) Stephan Walter 2023-03-23 14:15:48 +00:00
  • e60c31af70
         Generate library with CMake nusu-github 2023-03-23 23:12:49 +09:00
  • 632a3257e1
         Add also model/tokenizer.model to SHA256SUMS + update README Pavol Rusnak 2023-03-23 15:10:32 +01:00
  • d442e0210c
         Remove alpaca json Stephan Walter 2023-03-23 14:58:23 +01:00
  • 2580d75522
         Remove ggml files until the can be verified Stephan Walter 2023-03-23 14:55:55 +01:00
  • e0607ae91a Revert "Delete SHA256SUMS for now (#416)" Stephan Walter 2023-03-23 14:54:20 +01:00
  • 128c503392
         Fix quantize script not finding models in parent directory Jed Fox 2023-03-23 09:03:26 -04:00
  • f7dda362f2
         Merge branch 'ggerganov:master' into patch-1 RSereno 2023-03-23 12:51:42 +00:00
  • 2eb9d043d3
         fix comment anzz1 2023-03-23 14:20:44 +02:00
  • 8f0c8bcc8e
         unknown and invalid param exit codes 0 -> 1 anzz1 2023-03-23 14:09:49 +02:00
  • c96a80a3c6
         feat: '--in-prefix STRING' option anzz1 2023-03-23 13:59:09 +02:00
  • 2d01e60bc8
         command line args bounds checking anzz1 2023-03-23 13:49:27 +02:00
  • a140219e81
         Fix Makefile echo escape codes (by removing them). (#418) master-a140219 Kerfuffle 2023-03-23 05:41:32 -06:00
  • 8a3e5ef801
         Move model section from issue template to README.md (#421) Gary Mulder 2023-03-23 11:30:40 +00:00
  • 76e82a815b
         Fix GPTQ converter Timmy Knight 2023-03-23 01:19:36 -10:00
  • f58154abe0 Fix Makefile echo escape codes (by removing them). KerfuffleV2 2023-03-23 01:58:43 -06:00
  • 8eea5ae0e5
         Delete SHA256SUMS for now (#416) anzz1 2023-03-23 12:26:19 +02:00
  • dbb0683293 Updates to README.md model section Gary Mulder 2023-03-23 09:34:50 +00:00
  • f2df89685f
         (Windows) Set console to UTF-8 on init anzz1 2023-03-23 11:09:09 +02:00
  • 5d307f1815
         Update custom.md Gary Mulder 2023-03-23 09:02:41 +00:00
  • 93208cfb92
         Adjust repetition penalty .. Georgi Gerganov 2023-03-23 10:46:58 +02:00
  • 47ea33ab59
         Update README.md LostRuins 2023-03-23 16:02:19 +08:00
  • 03ace14cfd
         Add link to recent podcast about whisper.cpp and llama.cpp Georgi Gerganov 2023-03-23 09:48:51 +02:00
  • 10526e8c00
         Delete SHA256SUMS for now anzz1 2023-03-23 09:39:23 +02:00
  • 66ea164e1d Kahan summation on Q4_1 q4_1_more_accel_kahan Matvey Soloviev 2023-03-23 04:28:51 +01:00
  • e4412b45e3
         CI: CMake: Separate build and test steps (#376) master-e4412b4 anzz1 2023-03-23 04:20:34 +02:00
  • 711224708d Break up loop for numeric stability q4_1_more_accel_loopsplit Matvey Soloviev 2023-03-23 03:14:44 +01:00
  • ad2210bfda
         CI: CMake: Separate Build and Test steps anzz1 2023-03-23 03:33:05 +02:00
  • 859e70899a start doing the instructions but not finished. This probably doesnt compile strikingLoo 2023-03-22 17:52:46 -07:00
  • 80744d6fed
         Merge branch 'ggerganov:master' into master taher 2023-03-22 17:50:00 -07:00
  • 88df270f6b
         add space to comment rabidcopy 2023-03-22 19:44:00 -05:00
  • 666c5a0395
         Merge branch 'master' into interactive-eos-fix rabidcopy 2023-03-22 19:31:47 -05:00
  • f7dc43bc0d
         Fix instruct mode broken by PR #354 (#409) master-f7dc43b tjohnman 2023-03-23 01:30:23 +01:00
  • 84ab887349 merge strikingLoo 2023-03-22 17:22:45 -07:00
  • 7864eef92c
         tokenize newline token rabidcopy 2023-03-22 19:19:49 -05:00
  • 8f83ce8380
         remove newline token rabidcopy 2023-03-22 18:53:10 -05:00
  • 10206d0360
         remove newline token rabidcopy 2023-03-22 18:52:51 -05:00
  • 6a4cfc4dfa
         not needed rabidcopy 2023-03-22 18:02:35 -05:00
  • 4e4cfdfb67
         tokenize and inject reverse prompt as needed rabidcopy 2023-03-22 17:46:23 -05:00
  • 69071d3b6b Squeeze out about 5% more performance in Q4_1 inference Matvey Soloviev 2023-03-21 22:55:35 +01:00
  • ce339001c4 Fix instruct mode broken by PR #354 Johnman 2023-03-22 22:23:14 +01:00
  • ae1519f681
         Update tools.sh RSereno 2023-03-22 20:29:20 +00:00
  • 9ea43d4d91 Add support to batch size for perplexity Gary Linscott 2023-03-22 12:09:42 -07:00
  • ee8a788786
         Update issue template so people will use it (#404) Gary Mulder 2023-03-22 19:06:18 +00:00
  • a6bd606cd0
         typo Stephan Walter 2023-03-22 19:02:39 +00:00
  • 49197bbd6b
         Update custom.md Gary Mulder 2023-03-22 18:06:15 +00:00
  • 84ba1fd25b add capabiliy to convert from ggml back to torch or hf format for further consumption/training/finetuning Tai Duc Nguyen 2023-03-22 13:38:39 -04:00
  • 3a0dcb3920
         Implement server mode. tcp_server Thiago Padilha 2023-03-22 10:41:26 -03:00
  • bf44faa0ee
         Remove direct access to std streams from "run" Thiago Padilha 2023-03-22 09:55:45 -03:00