root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-11 19:21:46 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Commit Graph

  • 4e58a05249
         Allow overriding CC_TURING Henri Vasserman 2023-08-11 10:16:02 +0300
  • b815e97c3d
         Merge 'origin/master' into hipblas Henri Vasserman 2023-08-11 10:00:07 +0300
  • dae9dffa6a rename koboldcpp.dll to koboldcpp_default.dll Concedo 2023-08-11 14:54:27 +0800
  • e7d346c37c gguf : start implementing gguf_file_saver (WIP) M. Yusuf Sarıgöz 2023-08-11 09:52:01 +0300
  • c299c4ac0d
         New __dp4a assembly Engininja2 2023-08-11 09:43:14 +0300
  • e6b6ae55f4
         Undo mess Henri Vasserman 2023-08-11 09:30:28 +0300
  • a07f603a3e Replace vk::QueueFamilyIgnored with VK_QUEUE_FAMILY_IGNORED to support more Vulkan header versions 0cc4m 2023-08-11 05:29:26 +0200
  • 23e0eba66b
         git wasn't needed and didn't do anything William Behrens 2023-08-10 21:46:42 -0500
  • b19bf60881
         Merge branch 'ggerganov:master' into master William Behrens 2023-08-10 21:43:23 -0500
  • 084ee1b21a
         copy build info to output William Behrens 2023-08-10 21:43:17 -0500
  • 582ba1b478 metal : return null if load pipeline failed jhen 2023-08-11 07:22:47 +0800
  • 400dcced7e
         Merge branch 'ggerganov:master' into master Eve 2023-08-10 17:42:13 -0400
  • 9ca4abed89
         Handle ENABLE_VIRTUAL_TERMINAL_PROCESSING more gracefully on earlier versions of Windows. master-9ca4abe DannyDaemonic 2023-08-10 13:11:36 -0700
  • f316b94c7c gguf : rm deprecated function M. Yusuf Sarıgöz 2023-08-10 20:20:22 +0300
  • cfb8e35b73 gguf : inference with 7B model working (WIP) M. Yusuf Sarıgöz 2023-08-10 19:56:56 +0300
  • 52801c055d
         Merge pull request #1 from jrudolph/convert-llama2-vocab byte-6174 2023-08-10 12:33:02 -0400
  • 212500e454 remove redunct entry Equim 2023-08-11 00:26:18 +0800
  • f7de84bb8c server: fixed wrong variable name in timing json Equim 2023-08-10 23:59:00 +0800
  • 42cc04d11d gguf : calculate n_mult M. Yusuf Sarıgöz 2023-08-10 18:49:08 +0300
  • 22de6c5c4c upd .gitignore M. Yusuf Sarıgöz 2023-08-10 18:09:49 +0300
  • 4c0f64e302 rm binary commited by mistake M. Yusuf Sarıgöz 2023-08-10 18:07:41 +0300
  • 4f865181aa gguf : start implementing libllama in GGUF (WIP) M. Yusuf Sarıgöz 2023-08-10 17:49:31 +0300
  • aa26201291
         also support loading from llama2.c vocabulary Johannes Rudolph 2023-08-10 16:32:44 +0200
  • e59fcb2bc1
         Add --n-predict -2 for stopping generation on full context (#2565) master-e59fcb2 Christian Demsar 2023-08-10 10:28:27 -0400
  • d2b95e7e70
         refactor vocab loading into its own method Johannes Rudolph 2023-08-10 16:17:26 +0200
  • 886f4eed79 updated lite, up ver, remove bell Concedo 2023-08-10 22:01:33 +0800
  • aab15de466 commandline argument changes for clarity. Aniket 2023-08-10 09:53:21 -0400
  • 1c4d8bf981 gguf : start implementing libllama in GGUF (WIP) M. Yusuf Sarıgöz 2023-08-10 16:52:08 +0300
  • db5d7ab3f7 Adding more information in the README to use conversion tool. Aniket 2023-08-10 09:49:14 -0400
  • 1638757767
         Fix grammar-based sampling issue in server (#2566) master-1638757 Martin Krasser 2023-08-10 12:16:38 +0200
  • 42e055d9d6
         ws fix Henri Vasserman 2023-08-10 12:14:40 +0300
  • f41920e3a9
         AMD assembly optimized __dp4a Engininja2 2023-08-10 12:11:27 +0300
  • 29a59b5f07
         Fix merge Henri Vasserman 2023-08-10 12:09:28 +0300
  • c5f5209d37 globalize args Concedo 2023-08-10 16:30:02 +0800
  • 2c8e92044e Merge remote-tracking branch 'elsagranger/master' Laura 2023-08-10 07:59:55 +0200
  • 996072c250 metal : return null instead of exit(1) jhen 2023-08-10 08:45:50 +0800
  • 01f45e1c87 manual merge with llama.cpp master netrunnereve 2023-08-09 19:54:42 -0400
  • 8f8ab6c4c0
         hipLDFLAG Path change Unix to multisystem in Makefile YellowRoseCx 2023-08-09 18:05:03 -0500
  • acea8e10a3 examples/main: Add --prompt-cache-clobber parameter crasm 2023-08-07 21:12:43 -0400
  • 610ba4cfc4
         Merge 'origin/master' into hipblas Henri Vasserman 2023-08-09 23:54:58 +0300
  • 916a9acdd0
         ggml-alloc: Don't try to re-use buffers of external tensors (#2562) master-916a9ac Sam Spilsbury 2023-08-09 23:47:42 +0300
  • ea04a4ca19
         add log_callback to llama_context_params for custom logging. (#2234) master-ea04a4c grahameth 2023-08-09 22:46:40 +0200
  • b810424edf
         ggml-alloc: >= when checking for out-of-bounds Sam Spilsbury 2023-08-09 23:33:33 +0300
  • 198f162065
         add missing git dependency to flake.nix William Behrens 2023-08-09 11:53:20 -0500
  • 6309f7500c
         output build-info.h into cmake_current_binary_dir for easier packaging William Behrens 2023-08-09 11:50:04 -0500
  • d9b5744de0
         add build-info.h to flake post install William Behrens 2023-08-09 11:37:45 -0500
  • 20b8ff5064
         Add headers to nix packages William Behrens 2023-08-09 11:10:35 -0500
  • fd026f419d Handle ENABLE_VIRTUAL_TERMINAL_PROCESSING more gracefully on earlier versions of Windows. Danny Daemonic 2023-08-09 08:12:14 -0700
  • 57782c0bcb CUDA: Removed obsolete cmake CUDA arch JohannesGaessler 2023-08-09 17:07:09 +0200
  • a07e6dd3ad revert cuda changes as they are bugggy Concedo 2023-08-09 22:36:41 +0800
  • f8376c7e61 up ver, fixed compile (+1 squashed commits) Concedo 2023-08-09 21:23:33 +0800
  • 7715eced38 Fix grammar-based sampling issue in server Martin Krasser 2023-08-09 15:14:21 +0200
  • ba09f1c807 Merge branch 'master' into concedo_experimental Concedo 2023-08-09 21:18:34 +0800
  • a3fa0abaaa for got to add newline Aniket 2023-08-09 09:16:30 -0400
  • 3a7853d259 handle stablecode-completion-alpha-3b Concedo 2023-08-09 21:07:57 +0800
  • 40a51ec6a3 adding CMakeLists.txt file in the conversion script directory Aniket 2023-08-09 09:06:47 -0400
  • afb8f6ee6a removing 1 whitespace Aniket 2023-08-09 09:06:10 -0400
  • 7d0404c393 adding newline in readme Aniket 2023-08-09 09:05:37 -0400
  • 7b1f062620 adding add_subdirectory in examples dir CMakeLists.txt Aniket 2023-08-09 09:04:24 -0400
  • d551906b7b
         Merge 6383bbfa5f into 25d43e0eb5 jon-chuang 2023-08-09 17:27:15 +0800
  • 84f7995e48 Change LTO to option and other stuff Henri Vasserman 2023-08-09 11:24:08 +0300
  • 7674422f3e Merge remote-tracking branch 'origin/master' into zig-fixes Henri Vasserman 2023-08-09 10:52:39 +0300
  • 25d43e0eb5
         CUDA: tuned mul_mat_q kernels (#2546) master-25d43e0 Johannes Gäßler 2023-08-09 09:42:34 +0200
  • 90058d96b0 sleep longer before exit Concedo 2023-08-09 15:28:07 +0800
  • 2d71bf95cb Add --n-predict -2 for stopping generation on full context crasm 2023-08-09 02:17:56 -0400
  • 487cd25086 metal : print error of load pipeline state jhen 2023-08-09 13:17:23 +0800
  • 19cf2a8663 add idle field and up ver Concedo 2023-08-09 12:42:59 +0800
  • 4b8a354895 cudatoolkit version Concedo 2023-08-09 12:25:21 +0800
  • 159ad9269d up ver, set the cuda pool malloc lookahead back to 5% instead of 2% (+1 squashed commits) Concedo 2023-08-09 11:50:12 +0800
  • 49f0bfd69d
         Update README.md Eve 2023-08-08 22:58:53 -0400
  • 3919e67421
         Update README.md Eve 2023-08-08 22:58:46 -0400
  • 193f295a3a
         Update llama.cpp Eve 2023-08-08 22:47:34 -0400
  • be26777a6a add pp_threads support to other files netrunnereve 2023-08-08 22:19:59 -0400
  • d854348992 perplexity only uses pp_threads netrunnereve 2023-08-08 21:30:12 -0400
  • 5624a29c1f
         Merge branch 'ggerganov:master' into master Eve 2023-08-08 21:13:28 -0400
  • d14c066f0c cleaning up to remove spaces and satisfy failed checks Aniket 2023-08-08 20:40:17 -0400
  • 829565b13d better SQL JohannesGaessler 2023-08-09 01:31:26 +0200
  • 4024f91a66
         Add intrinsics polyfills for AMD Henri Vasserman 2023-08-09 01:56:44 +0300
  • 0246d0dd6f
         gptneox-main.cpp : map tensor names klosax 2023-08-09 00:54:21 +0200
  • 7d5f4522dd
         convert-llama-h5-to-gguf.py : map tensor names klosax 2023-08-09 00:52:16 +0200
  • f4d137d98c
         convert-gptneox-h5-to-gguf.py : map tensor names klosax 2023-08-09 00:50:11 +0200
  • ece4fc185e
         map tensor names klosax 2023-08-09 00:48:33 +0200
  • ab6212864c
         Merge 'origin/master' into hipblas Henri Vasserman 2023-08-09 00:37:01 +0300
  • 28046d1e52
         Merge and update server-cfg Henri Vasserman 2023-08-09 00:36:11 +0300
  • 5520876c3c cleaning up Makefile empty space before mearge Aniket 2023-08-08 14:28:34 -0400
  • 08e94332fc cleaning up some earlier files used for experiments Aniket 2023-08-08 14:27:01 -0400
  • 088eb86fbe updating gitignore Aniket 2023-08-08 14:21:14 -0400
  • 223ddb77b3 updating makefile so my initial tests are not compiled Aniket 2023-08-08 14:19:30 -0400
  • 3c0c155309
         Merge branch 'ggerganov:master' into master byte-6174 2023-08-08 14:14:02 -0400
  • 9a09e6418f minor spacing update Aniket 2023-08-08 14:00:05 -0400
  • 2a0138e5ea updating readme for instructions for compilation and use Aniket 2023-08-08 13:52:20 -0400
  • ff9fae57d1 updating makefile so test scripts are not compiled Aniket 2023-08-08 13:45:00 -0400
  • 97c809448f add plotting files JohannesGaessler 2023-08-08 19:34:31 +0200
  • bb99064690 Merge branch 'fix-benchmark-matmult-constants' of https://github.com/goerch/llama.cpp into fix-benchmark-matmult-constants goerch 2023-08-08 19:13:21 +0200
  • ea62e6eca9 Fix constants for matmul benchmark to work with Q4_0 goerch 2023-08-08 19:13:16 +0200
  • 926d90fbab Merge branch 'master' into concedo_experimental Concedo 2023-08-09 01:09:04 +0800
  • da53236bf3 database writing works JohannesGaessler 2023-08-08 19:05:10 +0200
  • 793cfd136c fixed 70B detection again, try fix horde issues, fixed lite unicode issue, fixed cmake for cuda Concedo 2023-08-09 01:05:00 +0800
  • 465cadd44c Refactor special tokens tokenization Igor Pissolati 2023-08-08 12:46:18 -0300
  • ada6cce40f Replace trie with linear search Igor Pissolati 2023-08-08 11:43:29 -0300