Commit graph

  • 0f4c13fc43 Updated justfile, added script to set shell path, and fixed Cargo.toml version issue. ajasibley 2023-05-25 01:19:57 -07:00
  • 8b8f2f4cf5 up ver to 1.25.1 Concedo 2023-05-25 14:49:30 +08:00
  • 156d70b82b Always set RNG seed when restoring cached prompt in main example. KerfuffleV2 2023-05-25 00:00:54 -06:00
  • 76c73987bf Use the initial value of params.seed to determine if user supplied seed KerfuffleV2 2023-05-24 02:55:30 -06:00
  • e1ec489ef2 Use existing session behavior when in instruct or interact first mode KerfuffleV2 2023-05-23 07:05:44 -06:00
  • 2d79928982 Apply clang suggestions. KerfuffleV2 2023-05-21 05:38:01 -06:00
  • de5bf5bf68 Some improvements to loading the session with --prompt-cache KerfuffleV2 2023-05-21 05:20:56 -06:00
  • e6eeb234f1 Merge branch 'master' into concedo_experimental Concedo 2023-05-25 10:34:43 +08:00
  • d2da155661 upgraded clblast Concedo 2023-05-25 10:18:12 +08:00
  • 875b385d79
    Update README.md ajasibley 2023-05-24 17:37:37 -07:00
  • 9580a547d9 Updated README. ajasibley 2023-05-24 16:56:17 -07:00
  • 5d66c80d99 Cleaner up shell.nix by removing bash commands and replacing them with just recipes. ajasibley 2023-05-24 15:07:33 -07:00
  • f80ce7a4e0
    Merge branch 'origin/master' into hipblas Henri Vasserman 2023-05-25 00:02:50 +03:00
  • ff99507049
    [wip] open_llama_3b support Henri Vasserman 2023-05-24 21:35:46 +03:00
  • 37a34deaa0 added a second pyinstaller for my own use that uses a different python version. don't use this. Concedo 2023-05-24 23:34:11 +08:00
  • bf482d1786 revert klite newline bug, trying to add win7 support Concedo 2023-05-24 22:21:01 +08:00
  • 844f92688a subpattern fix Concedo 2023-05-24 16:48:39 +08:00
  • 2d727e69c1
    Update common.cpp CRGBS 2023-05-24 16:38:28 +08:00
  • ac7876ac20
    Update CLBlast to 1.6.0 (#1580) master-ac7876a Henri Vasserman 2023-05-24 10:30:09 +03:00
  • d04b3bbe5e disable mmap when failsafe mode selected from GUI Concedo 2023-05-24 15:04:17 +08:00
  • 04ff4fda39
    Update common.cpp CRGBS 2023-05-24 14:39:25 +08:00
  • 943e5471cd
    Update common.cpp CRGBS 2023-05-24 14:28:35 +08:00
  • c31bbe934b
    readme : add docs for chat-persistent.sh (#1568) Evan Jones 2023-05-24 02:24:01 -04:00
  • 1359b6aba5
    chat-persistent.sh : use bracket expressions in grep (#1564) Senemu 2023-05-24 06:16:22 +00:00
  • d973514da5
    Update common.cpp CRGBS 2023-05-24 14:12:47 +08:00
  • c826d5221c
    Update main.cpp CRGBS 2023-05-24 14:10:48 +08:00
  • dcdc11a493
    Update build.yml CRGBS 2023-05-24 13:27:49 +08:00
  • 9e14714e67
    Update main.cpp CRGBS 2023-05-24 13:26:53 +08:00
  • c0e8da7912
    Update README.md ajasibley 2023-05-24 04:41:50 +00:00
  • e8ef92a738
    Update README.md ajasibley 2023-05-24 04:30:05 +00:00
  • 988dd73d82
    Merge pull request #7 from plurigrid/cosmonic ajasibley 2023-05-24 04:28:26 +00:00
  • 2df76d9064 Removed Vespa project. Aja Sibley 2023-05-24 04:26:59 +00:00
  • 74ac17d3ad
    Merge pull request #5 from plurigrid/cosmonic barton ⊛ 2023-05-24 04:11:22 +00:00
  • b314cbfb60 updated lite to support variable streaming lengths Concedo 2023-05-24 11:28:35 +08:00
  • 025f974d68 Updated readme ajasibley 2023-05-23 20:24:13 -07:00
  • 5f727081bc Fixed env error ajasibley 2023-05-23 19:15:11 -07:00
  • 7a91429897 try to do grpc completion Liu Ming 2023-05-24 10:13:31 +08:00
  • 0549bf3c09 Merge remote-tracking branch 'origin/master' Liu Ming 2023-05-24 08:49:38 +08:00
  • 968f310eb7 Merge commit '2e6cd4b025' Liu Ming 2023-05-24 08:49:27 +08:00
  • 3d6d096ab8 Update shell.nix ajasibley 2023-05-23 23:10:25 +00:00
  • e28bb0559c
    fix Henri Vasserman 2023-05-24 01:53:31 +03:00
  • b3329f5ca4
    rename path Henri Vasserman 2023-05-24 01:48:44 +03:00
  • 1b2d6f3d52
    Update CLBlast to 1.6.0 Henri Vasserman 2023-05-24 01:41:14 +03:00
  • b45efa3239 Updated nix.shell ajasibley 2023-05-23 22:20:17 +00:00
  • 75649f44b6
    Change CMake files Henri Vasserman 2023-05-24 01:14:04 +03:00
  • 8502d5178e fix args zrm 2023-05-23 17:09:52 -04:00
  • 2c1b5ae197 silence robot zrm 2023-05-23 17:08:37 -04:00
  • 8d7b28c28d
    Fixed some types in the params. Randall Fitzgerald 2023-05-23 13:35:12 -07:00
  • 3537ad1821
    Merge branch 'ggerganov:master' into master Randall Fitzgerald 2023-05-23 13:31:14 -04:00
  • c97e10c50c Merge branch 'master' into concedo_experimental Concedo 2023-05-24 00:36:30 +08:00
  • abb9ad789c fixed other arch Concedo 2023-05-24 00:20:43 +08:00
  • 7d873811f3
    Fix handling of "invalid property" when creating OpenCL command queue (#1565) master-7d87381 Maarten ter Huurne 2023-05-23 18:01:15 +02:00
  • 0c0009e4b4 updated lite Concedo 2023-05-23 23:18:52 +08:00
  • add5f1bdc9
    Update examples/server/server.cpp Randall Fitzgerald 2023-05-23 07:34:41 -07:00
  • 421e66b330
    Update examples/server/server.cpp Randall Fitzgerald 2023-05-23 07:34:36 -07:00
  • 355007b019 added sampler seed Concedo 2023-05-23 21:52:26 +08:00
  • cd4012c3ed minor fixes to debug logging, fixed a typo, added a new failsafe mode Concedo 2023-05-23 21:31:42 +08:00
  • 2071d730fa
    Forgot to remove some testing code. Randall Fitzgerald 2023-05-23 06:22:30 -07:00
  • 1c3fdf8cfd
    Add all generation parameters to server.cpp and allow resetting context Randall Fitzgerald 2023-05-23 06:16:54 -07:00
  • 5bf9784381 Merge branch 'master' into concedo_experimental Concedo 2023-05-23 18:19:16 +08:00
  • c645f1e8c1 add grpc server 刘铭 2023-05-23 17:07:50 +08:00
  • d45df1b1f4 Renamed DMMV X/Y compilation options JohannesGaessler 2023-05-23 08:55:01 +02:00
  • 98bfee013b Fewer iters, more ops per iter JohannesGaessler 2023-05-21 12:01:14 +02:00
  • e199938a3a Define GGML_CUDA_DMMV_BLOCK_Y if not defined JohannesGaessler 2023-05-20 19:37:11 +02:00
  • 5d0cf9928b Removed hipblas compatibility code JohannesGaessler 2023-05-20 14:36:26 +02:00
  • 17dc4c52d3 Fixed cmake LLAMA_CUDA_BY option JohannesGaessler 2023-05-20 14:31:11 +02:00
  • 82cf01f897 loop unrolling JohannesGaessler 2023-05-19 20:26:49 +02:00
  • 1a787101cc block y dim JohannesGaessler 2023-05-19 17:24:05 +02:00
  • fbf5588abc xor hack JohannesGaessler 2023-05-19 12:59:37 +02:00
  • ba000f9941
    Update README.md Evan Jones 2023-05-22 23:46:30 -04:00
  • 6a93b9f1a3 readme : add docs for chat-persistent.sh Evan Jones 2023-05-22 23:38:52 -04:00
  • 1176f37198 Fix handling of "invalid property" when creating OpenCL command queue Maarten ter Huurne 2023-05-22 23:55:33 +02:00
  • 2e6cd4b025
    OpenCL Token Generation Acceleration (#1459) master-2e6cd4b 0cc4m 2023-05-22 23:33:24 +02:00
  • bf1f02ddc0
    chat-persistent.sh : use bracket expressions in grep Senemu 2023-05-22 21:17:19 +00:00
  • 046def2d9a
    Merge branch 'master' of github.com:biw/llama.cpp into added-disable-tty Ben Williams 2023-05-22 14:03:36 -07:00
  • cb28080aef
    Small compiler warning fixes Henri Vasserman 2023-05-22 23:14:15 +03:00
  • 4dfd4fe1eb Restore default platform + device selection by id behavior 0cc4m 2023-05-22 21:51:39 +02:00
  • e1ee2810ea
    change to fprintf Henri Vasserman 2023-05-22 22:18:02 +03:00
  • 6d40cc3a44
    remove trailing whitespace xaedes 2023-05-22 20:56:35 +02:00
  • d3acbf644e
    simplify code xaedes 2023-05-22 20:53:57 +02:00
  • ee9aaaaebc Add conversion from FP32 quants to FP16 quants model Jason0214 2023-05-23 01:20:11 +08:00
  • 4a55951464 Only copy f16/f32 buffer if not already on GPU 0cc4m 2023-05-22 18:46:51 +02:00
  • 0651679302
    save checkpoint only when it was trained xaedes 2023-05-22 16:56:28 +02:00
  • cc440bd438
    fix bug in get_samples which corrupted training targets xaedes 2023-05-22 16:55:52 +02:00
  • b763d6f1f2
    remove unused functions xaedes 2023-05-22 16:54:21 +02:00
  • 7894e85788 fixed a bug in previous klite Concedo 2023-05-22 21:54:24 +08:00
  • a05da31fe7 updated embedded lite Concedo 2023-05-22 20:58:54 +08:00
  • 47e41fa8ce Add means to exit interactive mode changhz 2023-05-22 08:28:25 -04:00
  • b78ceb1a2e
    merge-hf-and-lora-to-hf.py FNsi 2023-05-22 19:31:17 +08:00
  • 29995194e3
    merge-hf-and-lora-to-hf.py FNsi 2023-05-22 19:29:24 +08:00
  • 1fd5d10b07
    Update merge-hf-and-lora-to-hf.py FNsi 2023-05-22 19:27:45 +08:00
  • 39287b06da
    Update merge-hf-and-lora-to-hf.py FNsi 2023-05-22 19:26:00 +08:00
  • e20e302e87 Merge branch 'master' into concedo_experimental Concedo 2023-05-22 17:05:34 +08:00
  • b9f06a7670 mavx only for windows by default, let them eat march native. Concedo 2023-05-22 16:48:55 +08:00
  • 981d5ba866 Merge remote-tracking branch 'occam/opencl-dev' into concedo_experimental Concedo 2023-05-22 16:16:48 +08:00
  • 169a26d15f removed unused build targets Concedo 2023-05-22 13:53:10 +08:00
  • b6a30489a7
    merge-hf-and-lora-to-hf.py FNsi 2023-05-22 13:08:59 +08:00
  • 587308a202 fixed some build errors on linux, changed icon resolution, added more error printing Concedo 2023-05-22 12:18:42 +08:00
  • 9d058c2096 avoid sending finalize op to thread pool if it does nothing zrm 2023-05-21 18:11:03 -04:00
  • 0d23f8ce8d disable mmap prefetch/readahead for NUMA systems zrm 2023-05-21 16:33:10 -04:00