root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-12 19:50:17 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Commit Graph

  • 8dd8ab1659 Various enhancement and integration pygmalion.cpp Concedo 2023-04-03 00:04:43 +0800
  • d62a050144 Remove hardcoded memory requirements table saharNooby 2023-04-02 18:37:45 +0400
  • b31447507a Update gptq to ggml loader as well albanD 2023-04-02 09:32:27 -0400
  • 1262ad0456 Fix build errors and warnings saharNooby 2023-04-02 17:23:39 +0400
  • f2b1dad22b Add GitHub workflows file saharNooby 2023-04-02 16:56:04 +0400
  • 1ca5102d83 Revert "Add mmap support for model files" anzz1 2023-04-02 15:40:09 +0300
  • a084358394 Revert "Fix ggml_init_params in quantize" anzz1 2023-04-02 15:40:04 +0300
  • 28e787574b Revert "Make mmap_file static" anzz1 2023-04-02 15:39:59 +0300
  • 7ae9e74031 Revert "Unmap the file in llama_free" anzz1 2023-04-02 15:39:53 +0300
  • 9569171712 Revert "Always initialize mm_addr and mm_length in llama_model" anzz1 2023-04-02 15:39:46 +0300
  • c94f7e98c1 Revert "Initial windows support (untested)" anzz1 2023-04-02 15:39:40 +0300
  • 17b98ca9ff Revert "Make loading weights 10-100x faster" anzz1 2023-04-02 15:39:28 +0300
  • 255f019f88 Revert "Ensure --mlock works properly with mmap() support" anzz1 2023-04-02 15:35:09 +0300
  • 91b98380b9 Revert "Introduce GGML migration tool for new file format" anzz1 2023-04-02 15:35:01 +0300
  • 6b4ebc328a Update README.md saharNooby 2023-04-02 15:28:34 +0400
  • e0684e8104 Add text generation and chat scripts saharNooby 2023-04-02 15:03:31 +0400
  • 126ebdf31d fix windows build Vladimir 2023-04-01 19:45:33 +0200
  • c87def0098 using github Pithikos/C-Thread-Pool for threading Vladimir 2023-03-31 21:03:48 +0200
  • d8d4e865cd
         Add a missing step to the gpt4all instructions (#690) Thatcher Chamberlin 2023-04-02 06:48:57 -0400
  • a88d3cffee Add -n to alpaca and gpt4all scripts niansa/tuxifan 2023-04-02 10:35:47 +0000
  • e986f94829
         Added api for getting/setting the kv_cache (#685) master-e986f94 Christian Falch 2023-04-02 12:23:04 +0200
  • c0bb1d3ce2
         ggml : change ne to int64_t (#626) master-c0bb1d3 Marian Cepok 2023-04-02 12:21:31 +0200
  • 4912f9d5f0
         fix whitespace Pavol Rusnak 2023-04-02 12:18:54 +0200
  • 3f4967b827 added new binaries Concedo 2023-04-02 17:14:38 +0800
  • bb965cc120 Merge branch 'master' into concedo Concedo 2023-04-02 17:13:28 +0800
  • ee46ad208e Add quantization test back, run ggml tests on first context init saharNooby 2023-04-02 13:05:17 +0400
  • 9aabb0d9db massive refactor completed, GPT-J integrated Concedo 2023-04-02 17:03:30 +0800
  • 1ecbad3a65 Remove unused files saharNooby 2023-04-02 12:53:41 +0400
  • 935d16f5db Move library wrapper to separate file, refactor code saharNooby 2023-04-02 12:24:40 +0400
  • 6e7801d08d
         examples : add gpt4all script (#658) Leonardo Neumann 2023-04-02 04:56:20 -0300
  • 81040f10aa
         llama : do not allocate KV cache for "vocab_only == true" (#682) master-81040f1 Stephan Walter 2023-04-02 07:18:53 +0000
  • c4f89d8d73
         make : use -march=native -mtune=native on x86 (#609) master-c4f89d8 Fabian 2023-04-02 09:17:05 +0200
  • 14a1150a51
         Update README.md Shreyas T 2023-04-02 10:41:53 +0530
  • 94cc34556d
         Update README.md Shreyas T 2023-04-02 10:40:15 +0530
  • d39fa6ab79
         Update README.md Shreyas T 2023-04-02 09:58:32 +0530
  • 8953022c8c
         Update README.md Shreyas T 2023-04-02 09:57:02 +0530
  • 399237fbf8
         Update README.md Shreyas T 2023-04-02 09:56:10 +0530
  • eeb6e64545
         Update README.md Shreyas T 2023-04-02 09:55:08 +0530
  • 0edb15b61d
         Update README.md Shreyas T 2023-04-02 09:54:42 +0530
  • 445c0cd75a
         Update README.md Shreyas T 2023-04-02 09:53:31 +0530
  • 5b70e7de4c
         fix default params for examples/main (#697) master-5b70e7d Murilo Santana 2023-04-01 23:41:12 -0300
  • cd12f6e7be Change sys.exit(1) to raise SystemExit(1) mrcichon 2023-04-02 04:11:39 +0200
  • f87d539a6d fix default params for examples/main Murilo Santana 2023-04-01 22:29:16 -0300
  • 452b6ab115 Use safe loading for .pth checkpoint albanD 2023-04-01 20:25:28 -0400
  • d282143a87
         Add a missing step to the gpt4all instructions Thatcher Chamberlin 2023-04-01 17:04:52 -0400
  • 9523d72b56
         top_k = 1 since it is an integer Fabio Rossini Sluzala 2023-04-01 17:21:37 -0300
  • 3300247e97
         Fix for temp == 0 Fabio Rossini Sluzala 2023-04-01 17:01:12 -0300
  • f370a670be Reviewer suggestion: Moved to examples Sebastian Apel 2023-04-01 21:18:42 +0200
  • 5833baeeec Feature: Param for numer of iterations, Bugfix for use of parameter threads Sebastian Apel 2023-04-01 21:06:47 +0200
  • 100dc551e1 Review comment: Removed set_locale Sebastian Apel 2023-04-01 20:33:11 +0200
  • 6e691af997 Reviewer input: removed rtsc, use epsilon for check Sebastian Apel 2023-04-01 20:27:19 +0200
  • d3bc4df97d fix windows build Vladimir 2023-04-01 19:45:33 +0200
  • a65d37ad36 using github Pithikos/C-Thread-Pool for threading Vladimir 2023-03-31 21:03:48 +0200
  • 21e88c8b0f
         run sanitizers in release, otherwise too slow (#5) Vladimir 2023-04-01 20:16:36 +0200
  • b1f08813e3 added support for gpt4all original format Concedo 2023-04-02 00:53:46 +0800
  • a463fb7668
         Update llama.h Christian Falch 2023-04-01 18:46:47 +0200
  • 17f463a083
         Update llama.h Christian Falch 2023-04-01 18:46:37 +0200
  • f411251bcf
         Update llama.cpp Christian Falch 2023-04-01 18:46:24 +0200
  • a0c895c087
         Update llama.cpp Christian Falch 2023-04-01 18:46:14 +0200
  • a717cba844
         py: huggingface -> Hugging Face (#686) Ikko Eltociear Ashimine 2023-04-02 01:38:18 +0900
  • c928ab8a38 Allow larger tensor sizes. Marian Cepok 2023-04-01 18:36:47 +0200
  • 38f9d02d52 Fix quantization from FP16 saharNooby 2023-04-01 20:01:06 +0400
  • 458f7cd7ab
         update convert-ggml-to-pth.py Ikko Eltociear Ashimine 2023-04-02 00:44:40 +0900
  • 14804b7978 Added api for retrieving and setting the kv cache chrfalch 2023-04-01 17:39:17 +0200
  • 972e28d48d Implement INT4 conversion and inference saharNooby 2023-04-01 19:22:01 +0400
  • 3ef747808a Be nice to CI machines by not allocating buffers Stephan Walter 2023-04-01 17:00:01 +0200
  • d0a7f742e7
         readme: replace termux links with homepage, play store is deprecated (#680) rimoliga 2023-04-01 11:57:30 -0300
  • 889eaac8f8
         Update README.md rimoliga 2023-04-01 11:47:34 -0300
  • 0d054e292e Show error message when -f fails master-0d054e2 Slaren 2023-03-31 20:03:48 +0200
  • b164bf4e27 Allocate memory as needed for specific configuration of model saharNooby 2023-04-01 17:15:23 +0400
  • ab9ad077c2
         Update README.md rimoliga 2023-04-01 10:03:28 -0300
  • d5349f8735 Fix Windows build by not using variable array sizes Stephan Walter 2023-04-01 14:36:28 +0200
  • a1e1d34c93 Add Python wrapper for C library saharNooby 2023-04-01 16:02:22 +0400
  • 39f91e3f6e Clean up QK and file and tensor types Stephan Walter 2023-04-01 14:00:24 +0200
  • 7130a89d1f [FILE FORMAT CHANGED] Reverse dimensions in ggml file (makes it more similar to llama.cpp format) saharNooby 2023-04-01 14:41:30 +0400
  • ac03019fcf Move model to separate C library file saharNooby 2023-04-01 14:38:50 +0400
  • f6d45baec0 Support FP16 inference saharNooby 2023-04-01 11:53:49 +0400
  • fe98c94a63 [FILE FORMAT CHANGED] Use ggml_get_rows to get embedding saharNooby 2023-04-01 11:28:32 +0400
  • 16ec7a5c18 Add fail-fast version of the test saharNooby 2023-04-01 11:15:15 +0400
  • 0fcb7c64c6 Remove reference implementation code and test against pre-created logits saharNooby 2023-04-01 11:09:24 +0400
  • 0fb5433e97 miss some changes in the previous commit Howard Su 2023-04-01 15:09:06 +0800
  • bf88e8a246 Update README.md saharNooby 2023-04-01 10:12:10 +0400
  • 6fe9486cee Finally, FP32 inference saharNooby 2023-04-01 10:06:39 +0400
  • 085a9f90a7 still refactoring Concedo 2023-04-01 11:56:34 +0800
  • 6e6125ebdb updated pyinstaller to clean temp dir,removed warning flags from makefile because they are just clutter. Concedo 2023-04-01 09:25:41 +0800
  • 9ab6e87b58 Merge branch 'master' into concedo Concedo 2023-04-01 09:05:45 +0800
  • 801b178f2a still refactoring, but need a checkpoint to prepare build for 1.0.7 Concedo 2023-04-01 08:55:14 +0800
  • 6a498f0d79 Remove torch GPU dependencies bsilvereagle 2023-03-31 15:51:41 -0700
  • b09da81d52
         Use getopts for example scripts Ben Siraphob 2023-03-31 17:37:33 -0500
  • 3525899277
         Enable -std= for cmake builds, fix warnings (#598) master-3525899 Stephan Walter 2023-03-31 19:19:16 +0000
  • e80b06305d Enable -std= for cmake builds, fix warnings Stephan Walter 2023-03-29 17:44:04 +0200
  • 7e30f52600
         examples: add gpt4all script Leonardo Neumann 2023-03-31 15:51:20 -0300
  • 2d2d61568c Show error message when -f fails Slaren 2023-03-31 20:03:48 +0200
  • 41e8d2b434 Move constant out of loop Howard Su 2023-04-01 01:51:44 +0800
  • 8febfc73af Fix inplace version of operators Howard Su 2023-04-01 01:26:48 +0800
  • 6b86f5ea22 halfway refactoring, wip adding other model types Concedo 2023-04-01 01:13:05 +0800
  • 61c6b1a4e0 Add comparison against reference implementation script, implement state & logits saving saharNooby 2023-03-31 20:23:42 +0400
  • d00f28581a Add reference implementation of RWKV RNN saharNooby 2023-03-31 19:57:16 +0400
  • 1d08882afa
         Optimize AVX2 ggml_vec_dot_q4_0 (#642) master-1d08882 slaren 2023-03-31 17:55:52 +0200
  • fd2f59a03d Reviewer requests: added parameter for threads, switched to ggml_time_us() Sebastian Apel 2023-03-31 17:38:19 +0200