root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-05 16:24:34 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

Commit Graph

  • a8815a683e
         Remove Arch Linux note DaniAndTheWeb 2023-05-05 18:31:48 +0200
  • 4e3c178be4
         Automatic Arch Linux detection for BLAS DaniAndTheWeb 2023-05-05 18:31:05 +0200
  • 851f55325a Merge remote-tracking branch 'temp/concedo' into concedo_experimental Concedo 2023-05-05 23:55:53 +0800
  • 534c89e766 Track character width Danny Daemonic 2023-05-05 08:38:58 -0700
  • 921dcee00a
         readme: add missing info (#1324) Pavol Rusnak 2023-05-05 16:43:36 +0200
  • 60196ae73d ggml: add AVX support katsu560 2023-05-05 23:39:07 +0900
  • 2edbcebe27 added optional force versioning flag Concedo 2023-05-05 22:02:00 +0800
  • 39f3d1cf48 Merge branch 'master' into concedo_experimental Concedo 2023-05-05 21:34:33 +0800
  • 2d13786e91
         Fix for OpenCL / clbast builds on macOS. (#1329) master-2d13786 Ionoclast Laboratories 2023-05-05 08:18:21 -0400
  • 8f9f962d4d Signed variable to unsigned variable cast Danny Daemonic 2023-04-29 17:48:52 -0700
  • 94dd17247a author mode -> multiline input Danny Daemonic 2023-04-23 07:05:02 -0700
  • 52e319050b Add author mode and other related QOL improvements Danny Daemonic 2023-04-18 02:55:40 -0700
  • 8131bc8b56 add new sampling algorithm mirostat Hendrik Langer 2023-05-05 13:23:47 +0200
  • 46da5de195
         Revert "quick readme update" CRD716 2023-05-04 21:30:51 -0500
  • a90e96b266
         Convert.py @staticmethod (#1327) Benjamin Lecaillon 2023-05-05 02:17:07 +0200
  • b05ec02a1b
         Update convert.py Ivan Stepanov 2023-05-05 03:06:26 +0300
  • 100fc2be5e
         Fix for OpenCL / clbast builds on macOS. Ionoclast Laboratories 2023-05-04 19:09:45 -0400
  • 94c5652fc0
         quantize: make output filename optional, default to ggml-model-<ftype>.bin (#1301) master-94c5652 slaren 2023-05-05 00:58:56 +0200
  • 893bf9d368
         Line 698 has one #staticmethod and should not Benjamin Lecaillon 2023-05-04 23:49:01 +0200
  • 47bbd631f2
         readme: add missing info Pavol Rusnak 2023-05-04 20:59:19 +0200
  • 34d9f22f44
         Wrap exceptions in std::exception to verbose output on exception. (#1316) master-34d9f22 Ivan Stepanov 2023-05-04 19:56:27 +0300
  • d3e8093e9b
         convert: support DT_BF16 tensors (#1309) Ivan Stepanov 2023-05-04 19:54:37 +0300
  • 360cfe5bec
         readme : add OpenBuddy link (#1321) 44670 2023-05-05 00:33:31 +0800
  • 92e2b38a9a
         more jank Henri Vasserman 2023-05-04 19:26:45 +0300
  • 52179eb4d9
         MSVC stuff Henri Vasserman 2023-05-04 19:05:43 +0300
  • ae28ec9429
         Update README.md 44670 2023-05-05 00:18:43 +0800
  • 2edbdb0f99
         main : add --in-suffix option (#1318) master-2edbdb0 44670 2023-05-04 23:41:12 +0800
  • 07b8ddb743
         Merge 'origin/master' into cistuff Henri Vasserman 2023-05-04 18:31:08 +0300
  • b0d9e4c322
         not sure why this is failing Henri Vasserman 2023-05-04 18:22:03 +0300
  • 20fbf2a2a0
         ggml : change immintrin.h to intrin.h for compatibility (#1307) master-20fbf2a Ron Jailall 2023-05-04 11:05:59 -0400
  • f8929309d7
         Download licenses to Henri Vasserman 2023-05-04 18:05:12 +0300
  • 42b1757522
         Remove testing from matrix Henri Vasserman 2023-05-04 16:37:15 +0300
  • 530ad68963 print input suffix before generation 44670 2023-05-04 21:23:30 +0800
  • c08fca9225 adding --in-suffix option 44670 2023-05-04 21:09:04 +0800
  • db1080876a
         Only escape prompts when used with -e (#1311) master-db10808 DannyDaemonic 2023-05-04 05:08:25 -0700
  • 795a644962 Avoid hardcoding a space at the beginning of the prompt. Ivan Stepanov 2023-05-04 14:57:55 +0300
  • 2d5418a69d Wrap exceptions in std::exception to verbose output on exception. Ivan Stepanov 2023-05-04 14:58:52 +0300
  • f0e44cdeda Remove const char* prompt Danny Daemonic 2023-05-04 04:47:53 -0700
  • 458aeb10e9 use pause asm insn in busyloop to run the CPU (13600K) 10 °C cooler Sami Farin 2023-05-04 13:51:29 +0300
  • becce0043e
         Update convert.py Ivan Stepanov 2023-05-04 13:50:43 +0300
  • e3c2421b9f
         Update convert.py Ivan Stepanov 2023-05-04 13:49:15 +0300
  • dd8902d3e4
         Update convert.py Ivan Stepanov 2023-05-04 13:46:33 +0300
  • a3ffcbd98b
         Merge branch 'master' into e-escape DannyDaemonic 2023-05-04 03:12:29 -0700
  • ccef5e653d Updated README.md example to use -e for Windows prompt Danny Daemonic 2023-05-04 03:06:21 -0700
  • 1b6f595230 Update main's README.md with new features (#1296) DannyDaemonic 2023-05-04 03:02:59 -0700
  • 938b7c2e9d fix #1224 reverse prompt and multi line (#1297) Tomas 2023-05-04 17:02:30 +0700
  • c65a7fbfa9
         Update main's README.md with new features (#1296) DannyDaemonic 2023-05-04 03:02:59 -0700
  • f647ce040f
         fix #1224 reverse prompt and multi line (#1297) master-f647ce0 Tomas 2023-05-04 17:02:30 +0700
  • 04c0d480d7
         Move all HIP stuff to ggml-cuda.cu Henri Vasserman 2023-05-04 12:31:16 +0300
  • d83cfbad0c
         Merge 'origin/master' into hipblas Henri Vasserman 2023-05-04 11:31:16 +0300
  • 76692c90cd q4_0c: avoid _mm512_loadu_epi64 instruction Håkon H. Hitland 2023-05-04 09:53:55 +0200
  • b63654c8df load pretrained vocab alex 2023-05-04 09:21:24 +0200
  • d53f76760d q4_0c: disable prefetching on M1 Håkon H. Hitland 2023-04-27 22:48:46 +0200
  • 2949725fea q4_0c: prefetch on AVX-512 and ARM Håkon H. Hitland 2023-04-24 18:17:31 +0200
  • 1b49d26f8a q4_0c: Arm Neon acceleration Håkon H. Hitland 2023-04-21 00:11:49 +0200
  • ab543dc1a4 q4_0c: AVX512 vec_dot and quantize impl Håkon H. Hitland 2023-04-18 23:07:03 +0200
  • 4bd781cd25 q4_0c: quantize support Håkon H. Hitland 2023-04-18 00:57:30 +0200
  • a1e6fb9281 q4_0c continous row layout Håkon H. Hitland 2023-04-17 23:36:29 +0200
  • 221946777c test-quantize: fix for q8_0 intermediates Håkon H. Hitland 2023-04-16 00:37:16 +0200
  • c8f7eeb7fd update kobold lite Concedo 2023-05-04 14:43:35 +0800
  • 981d71b281 Only escape prompts when used with -e Danny Daemonic 2023-05-03 23:23:24 -0700
  • e01dc631f7 Merge branch 'master' into concedo_experimental Concedo 2023-05-04 14:04:41 +0800
  • 7c129305f5 derp (+1 squashed commits) Concedo 2023-05-04 12:10:19 +0800
  • 3f30da38ad llama, main: save state incrementally Evan Jones 2023-05-03 02:09:19 -0400
  • 866fd3f3cb
         save a token CRD716 2023-05-03 21:19:27 -0500
  • c47b349281 Support DT_BF16 tensors Ivan Stepanov 2023-05-04 04:09:45 +0300
  • 932e616cf4
         Code Formatting Tomas 2023-05-04 07:27:52 +0700
  • 2b7cf9f32b fix too relaxed model glob (breaking multifile) alex 2023-05-04 00:16:12 +0200
  • aebb5d46ff
         fix typo in ggml.c Ron Jailall 2023-05-03 18:08:54 -0400
  • 286efed05c
         conditional def of intrin.h Ron Jailall 2023-05-03 18:06:40 -0400
  • b59c371035 add support for ByteStorage, relax model glob alex 2023-05-03 23:57:08 +0200
  • ca0a3e78d9
         change immintrin.h to intrin.h for compatibility Ron Jailall 2023-05-03 17:40:33 -0400
  • 31ff9e2e83
         ci : add cublas to windows release ci_cublas-31ff9e2 ci_cublas Green Sky 2023-05-01 12:41:46 +0200
  • 9f4505a0c6 fixed some bugs FSSRepo 2023-05-03 14:25:14 -0600
  • 799fdc1b5d
         ggml : vectorize Q8_0 quantization master-799fdc1 Georgi Gerganov 2023-05-03 23:24:20 +0300
  • 8dc342c069
         quick readme update CRD716 2023-05-03 15:08:02 -0500
  • f11c0f9aa1
         add model-agnostic dan prompt CRD716 2023-05-03 15:06:24 -0500
  • 45d94c8f6f
         ci : add cublas to windows release ci_cublas-45d94c8 Green Sky 2023-05-01 12:41:46 +0200
  • 44286d3bc5
         ci : add cublas to windows release ci_cublas-44286d3 Green Sky 2023-05-01 12:41:46 +0200
  • 6daa09d879
         examples : read chat prompts from a template file (#1196) khimaros 2023-05-03 10:58:11 -0700
  • cad6ff5d36 scripts : add ppl-run-all.sh Georgi Gerganov 2023-05-03 20:53:11 +0300
  • c2aa88189c read chat prompts from a template file khimaros 2023-04-18 14:48:23 -0700
  • 0652b4209f
         llama : require first token to be BOS Georgi Gerganov 2023-05-03 20:25:55 +0300
  • 3f870c55f8 quantize: make output filename optional, default to ggml-model-<ftype>.bin slaren 2023-05-03 18:43:11 +0200
  • bca9ad938a
         minor : fix whitespaces (#1302) Georgi Gerganov 2023-05-03 20:09:42 +0300
  • 32d8b3ff24
         minor : fix whitespaces Georgi Gerganov 2023-05-03 19:54:57 +0300
  • f684c4d414 Merge branch 'master' of https://github.com/FSSRepo/llama.cpp FSSRepo 2023-05-03 10:47:06 -0600
  • 197bb66339 Added readme for server example FSSRepo 2023-05-03 10:38:35 -0600
  • 3baa706a19
         Merge branch 'ggerganov:master' into master Steward Garcia 2023-05-03 10:35:19 -0600
  • e2a937ca6a
         minor : fix trailing whitespaces Georgi Gerganov 2023-05-03 18:43:23 +0300
  • ede8e4edbb Merge branch 'master' into concedo_experimental Concedo 2023-05-03 23:34:50 +0800
  • b0c71c7b6d
         scripts : platform independent script to verify sha256 checksums (#1203) KASR 2023-05-03 17:31:28 +0200
  • a8a2efdc81
         examples : various prompt and example fixes (#1298) CRD716 2023-05-03 10:26:47 -0500
  • 105f818d45 integrated new version of rwkv from upstream Concedo 2023-05-03 23:26:39 +0800
  • 773455084c
         use common characters CRD716 2023-05-03 08:41:01 -0500
  • c14ac96c2c
         miku prompt improvements CRD716 2023-05-03 08:37:24 -0500
  • 1abe47c8d9
         fix dan.txt CRD716 2023-05-03 08:33:27 -0500
  • 4857739ab5 allow specifying a different thread count for GPU blas Concedo 2023-05-03 21:19:59 +0800
  • b67cc50dad
         Merge 'origin/master' into hipblas Henri Vasserman 2023-05-03 15:04:51 +0300
  • b78af37cd2
         fix reverse prompt and multi line Tomas 2023-05-03 18:47:11 +0700