Commit Graph

Select branches

Hide Pull Requests

dev

feat-input-prefix

jed/load-progress

jed/spm

llama-patch-enable-fma-msvc

master

mmap

model-linking-policy-doc

patch-win-utf8

q4_1_more_accel

q4_1_more_accel_kahan

q4_1_more_accel_loopsplit

tcp_server

master-01a297b

master-074bea2

master-084e2f0

master-0b366e7

master-0f1b21c

master-22213a1

master-2456837

master-2e17dfd

master-2e664f1

master-305ba6f

master-368d0c8

master-3cd8dde

master-4122dff

master-483bab2

master-4870e45

master-50fae10

master-56e659a

master-5c19c70

master-69c9229

master-70f01cb

master-8cf9f34

master-928480e

master-9794052

master-9e17072

master-a140219

master-a791a68

master-ad072fc

master-ad5fd5b

master-ae44e23

master-c494ed5

master-d3f202d

master-d5850c5

master-d7def1a

master-da5303c

master-e4412b4

master-e6c9e09

master-ea10d3d

master-f5a77a6

master-f7dc43b

Mono Color

• b6b268d441
  Add link to Roadmap discussion master Georgi Gerganov 2023-03-24 09:13:35 +0200
• 3cd8dde0d1 Revert "Fix memory allocation issues and seg faults" master-3cd8dde Georgi Gerganov 2023-03-24 06:22:28 +0200
• f7de57fd3a
  Update README.md model-linking-policy-doc Gary Mulder 2023-03-23 22:29:52 +0000
• 4870e455b3
  Fix memory allocation issues and seg faults master-4870e45 Georgi Gerganov 2023-03-24 00:11:53 +0200
• 483bab2e3d
  Avoid the transposed X branch in the Z = X * Y matrix multiplication (#439) master-483bab2 Georgi Gerganov 2023-03-23 23:22:01 +0200
• 404e1da38e
  Fix quantize script not finding models in parent directory (#428) Jed Fox 2023-03-23 16:42:52 -0400
• 4cc053b6d5
  Remove oboslete command from Docker script Georgi Gerganov 2023-03-23 22:39:44 +0200
• 0ba5a3a9a5
  Obsolete Georgi Gerganov 2023-03-23 22:32:02 +0200
• 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 -0500
• 4a4718e8ab
  More correct load progress jed/load-progress Jed Fox 2023-03-23 16:18:37 -0400
• 23035f9ba8
  Use seekg to find file size instead Jed Fox 2023-03-23 16:18:29 -0400
• 20a1a4e09c
  Fix GPTQ converter (#423) master-ad072fc Timmy Knight 2023-03-23 10:18:13 -1000
• ad072fc5ad
  Generate library with CMake (#430) nusu-github 2023-03-24 05:16:48 +0900
• 1f9592baf3
  Renames Jed Fox 2023-03-23 16:15:55 -0400
• d6aa749ccf
  Swap from exclusions to allowlist jed/spm Jed Fox 2023-03-23 13:58:47 -0400
• ea10d3ded2
  Command line args bounds checking (#424) master-ea10d3d anzz1 2023-03-23 19:54:28 +0200
• ab02a2441c
  Move llama_progress_handler into llama_context_params Jed Fox 2023-03-23 13:36:43 -0400
• e47924fd4b
  File load progress reporting Jed Fox 2023-03-22 13:13:29 -0400
• 927bc26e03
  Add a Package.swift for SwiftPM support Jed Fox 2023-03-22 10:05:33 -0400
• a18c19259a Fix Nix build Ben Siraphob 2023-03-22 00:37:02 -0500
• a50e39c6fe
  Revert "Delete SHA256SUMS for now" (#429) Stephan Walter 2023-03-23 14:15:48 +0000
• 2eb9d043d3
  fix comment patch-win-utf8 anzz1 2023-03-23 14:20:44 +0200
• c96a80a3c6
  feat: '--in-prefix STRING' option feat-input-prefix anzz1 2023-03-23 13:59:09 +0200
• a140219e81
  Fix Makefile echo escape codes (by removing them). (#418) master-a140219 Kerfuffle 2023-03-23 05:41:32 -0600
• 8a3e5ef801
  Move model section from issue template to README.md (#421) Gary Mulder 2023-03-23 11:30:40 +0000
• 8eea5ae0e5
  Delete SHA256SUMS for now (#416) anzz1 2023-03-23 12:26:19 +0200
• f2df89685f
  (Windows) Set console to UTF-8 on init anzz1 2023-03-23 11:09:09 +0200
• 93208cfb92
  Adjust repetition penalty .. Georgi Gerganov 2023-03-23 10:46:58 +0200
• 03ace14cfd
  Add link to recent podcast about whisper.cpp and llama.cpp Georgi Gerganov 2023-03-23 09:48:51 +0200
• 66ea164e1d Kahan summation on Q4_1 q4_1_more_accel_kahan Matvey Soloviev 2023-03-23 04:28:51 +0100
• e4412b45e3
  CI: CMake: Separate build and test steps (#376) master-e4412b4 anzz1 2023-03-23 04:20:34 +0200
• 711224708d Break up loop for numeric stability q4_1_more_accel_loopsplit Matvey Soloviev 2023-03-23 03:14:44 +0100
• f7dc43bc0d
  Fix instruct mode broken by PR #354 (#409) master-f7dc43b tjohnman 2023-03-23 01:30:23 +0100
• 69071d3b6b Squeeze out about 5% more performance in Q4_1 inference q4_1_more_accel Matvey Soloviev 2023-03-21 22:55:35 +0100
• ee8a788786
  Update issue template so people will use it (#404) Gary Mulder 2023-03-22 19:06:18 +0000
• 3a0dcb3920
  Implement server mode. tcp_server Thiago Padilha 2023-03-22 10:41:26 -0300
• bf44faa0ee
  Remove direct access to std streams from "run" Thiago Padilha 2023-03-22 09:55:45 -0300
• b7f1fa6d8c
  Move llama_context setup + perplexity back to main.cpp Thiago Padilha 2023-03-22 09:39:25 -0300
• d7d53b84db
  Add main.cpp back and invoke "run" from it Thiago Padilha 2023-03-22 09:16:33 -0300
• 90175ee13f
  Move main.cpp to run.cpp Thiago Padilha 2023-03-22 09:05:50 -0300
• 69c92298a9
  Deduplicate q4 quantization functions (#383) master-69c9229 Stephan Walter 2023-03-22 17:29:06 +0000
• 97940520e8
  fix: add POSIX functionality for Linux compilation (#51) master-9794052 master-305ba6f Valentyn Bezshapkin 2023-03-22 18:20:25 +0100
• 305ba6f0e6
  Don't force immediate interactive without `-i` (#354) tjohnman 2023-03-22 18:16:35 +0100
• 4122dffff9
  cmake: make llama an actual library (#392) master-4122dff Erik Scholz 2023-03-22 17:37:10 +0100
• 56e659a0b2
  fix perplexity after c-api refactor (#390) master-56e659a Erik Scholz 2023-03-22 17:09:38 +0100
• 40ea807a97
  Add details on perplexity to README.md (#395) Gary Linscott 2023-03-22 08:53:54 -0700
• d5850c53ca
  Add missing header for memcpy (#386) master-d5850c5 Yusuf Kağan Hanoğlu 2023-03-22 11:55:45 +0300
• ae44e23ee3
  When seed <= 0 - use the clock to generate one master-ae44e23 master-928480e Georgi Gerganov 2023-03-22 07:47:15 +0200
• 928480ef5b
  Init llama_context_params properly from CLI (#370) Georgi Gerganov 2023-03-22 07:45:00 +0200
• 56817b1f88
  Remove temporary notice and update hot topics master-f5a77a6 Georgi Gerganov 2023-03-22 07:34:02 +0200
• f5a77a629b
  Introduce C-style API (#370) Georgi Gerganov 2023-03-22 07:32:36 +0200
• d1e4a1822d
  Add __SSE3__ macro for MSVC too because why not llama-patch-enable-fma-msvc anzz1 2023-03-22 05:47:05 +0200
• 6ceb761499
  MSVC cvt intrinsics anzz1 2023-03-22 04:36:29 +0200
• 82654f1f5a
  Enable F16C/CVT16 vector extensions on MSVC anzz1 2023-03-22 04:05:49 +0200
• cf5b08482f
  Enable Fused-Multiply-Add (FMA) instructions on MSVC anzz1 2023-03-22 03:46:48 +0200
• da0e9fe90c Add SHA256SUMS file and instructions to README how to obtain and verify the downloads Gary Mulder 2023-03-20 20:14:06 +0000
• e6c9e0986c Fix bin dir for win ci master-e6c9e09 anzz1 2023-03-21 23:49:24 +0200
• 01a297b099
  specify build type for ctest on windows (#371) master-01a297b Erik Scholz 2023-03-21 22:34:25 +0100
• 3366853e41
  Add notice about pending change Georgi Gerganov 2023-03-21 22:57:35 +0200
• 3f9c6135e4
  fix typo in chatLLaMa (#368) Mathieu Nayrolles 2023-03-21 16:52:27 -0400
• 0f61352708
  Update issue templates Georgi Gerganov 2023-03-21 19:47:27 +0200
• 353ec251a4
  We could use std::unordered_map over std::map (#305) Fabio R. Sluzala 2023-03-21 14:21:50 -0300
• 89d5d90f3b
  Fix color codes emitting mid-UTF8 code. (#312) Matvey Soloviev 2023-03-21 18:11:01 +0100
• 16ffc013c6
  Importer for GPTQ quantized LLaMA models (#301) comex 2023-03-21 09:42:25 -0700
• 486ae645fd
  Compute perplexity over prompt (#270) Gary Linscott 2023-03-21 09:27:42 -0700
• 3ab3e6582f
  Add chatLLaMa script (#198) Jean-Christophe Hoelt 2023-03-21 18:23:15 +0200
• f157088cb7
  makefile: Fix CPU feature detection on Haiku (#218) Alex von Gluck IV 2023-03-21 11:21:06 -0500
• c86ba036e6
  Enable ANSI colors on Windows 10+ (#311) anzz1 2023-03-21 18:14:46 +0200
• 1daf4dd712
  Minor style changes Georgi Gerganov 2023-03-21 18:10:32 +0200
• dc6a845b85
  Add chat.sh script Georgi Gerganov 2023-03-21 18:09:37 +0200
• 6a612959e1
  Check for reverse prompt by characters instead of tokens (#292) (#330) tjohnman 2023-03-21 17:05:06 +0100
• d5f56a5e5a
  Check for reverse prompt by characters instead of tokens (#292) (#330) tjohnman 2023-03-21 17:04:43 +0100
• 3bfa3b43b7
  Fix convert script, warnings alpaca instructions, default params Georgi Gerganov 2023-03-21 17:59:16 +0200
• 715d292ee0
  Add OpenBSD support (#314) Kevin Lo 2023-03-21 09:50:09 -0600
• c98ae02668
  fix typo in comment (#318) Mack Straight 2023-03-21 08:49:43 -0700
• c3b2306b18
  Makefile: slightly cleanup for Mac Intel; echo instead of run ./main -h (#335) Qingyou Meng 2023-03-21 23:44:11 +0800
• 975d2cebf9
  cmdline option for custom amount of model parts (--n_parts N) (#348) anzz1 2023-03-21 17:42:43 +0200
• e0ffc861fa
  Update IPFS links to quantized alpaca with new tokenizer format (#352) Kevin Kwok 2023-03-21 08:34:49 -0700
• 8f644a0a85
  Change default repeat_penalty to 1.0 Georgi Gerganov 2023-03-21 17:32:14 +0200
• eb34620aec
  Add tokenizer test + revert to C++11 (#355) Georgi Gerganov 2023-03-21 17:29:41 +0200
• 2e664f1ff4
  Add initial AVX512 support for dot product on Linux (#320) master-2e664f1 Casey Primozic 2023-03-21 07:35:42 -0700
• 8cf9f34edd
  Adding missing features of CMakeLists.txt & Refactoring (#131) master-8cf9f34 nusu-github 2023-03-21 09:37:16 +0900
• bd4b46d6ba Nix flake: set meta.mainProgram to llama Ben Siraphob 2023-03-20 16:44:30 -0500
• 6b6d5b5024
  Fixed tokenizer.model not found error when model dir is symlink (#325) Qingyou Meng 2023-03-21 03:33:10 +0800
• a791a68b61
  move file magic/version to header, print expected version (#319) master-a791a68 Mack Straight 2023-03-20 12:26:01 -0700
• 0f1b21cb90
  Docker - Fix publish docker image in GitHub Registry (#235) master-0f1b21c Bernat Vadell 2023-03-20 18:05:20 +0100
• 074bea2eb1
  sentencepiece bpe compatible tokenizer (#252) master-074bea2 Mack Straight 2023-03-20 03:17:23 -0700
• 5cb63e2493
  Add tqdm to Python requirements (#293) Stephan Walter 2023-03-20 08:24:11 +0000
• da5303c1ea
  bugfix: default should not be interactive (#304) master-da5303c cocktailpeanut 2023-03-19 17:44:20 -0400
• 4545539d71
  Rename script Georgi Gerganov 2023-03-19 21:58:51 +0200
• edeba28366
  Add temporary helper script for Alpaca chat Georgi Gerganov 2023-03-19 21:57:28 +0200
• 5c19c70ba6
  fix coloring of last `n_batch` of prompt, and refactor line input (#221) master-5c19c70 Rickey Bowers Jr 2023-03-19 13:44:30 -0600
• 24568371ae
  Support for multiple reverse prompts. (#299) master-2456837 tjohnman 2023-03-19 20:33:06 +0100
• 7392f1cd2c
  Improved quantize script (#222) master-ad5fd5b Suaj Carrot 2023-03-19 12:38:44 -0600
• ad5fd5b60c
  Make prompt randomization optional. (#300) tjohnman 2023-03-19 19:36:19 +0100
• 368d0c8a9e
  Respect the maximum number of tokens in interactive. (#298) master-368d0c8 tjohnman 2023-03-19 19:31:17 +0100
• 50fae10d03
  Add --ignore-eos parameter (#181) master-50fae10 slaren 2023-03-19 19:22:48 +0100
• 084e2f0ec0
  interactive mode: print '\n' in sigint_handler, this flush stdout thus ensure color reset. (#283) master-084e2f0 Qingyou Meng 2023-03-20 02:10:00 +0800
• 0b366e7357
  Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294) master-0b366e7 Erik Scholz 2023-03-19 18:57:00 +0100
• 160bfb217d
  Update hot topics to mention Alpaca support Georgi Gerganov 2023-03-19 19:51:55 +0200