ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-03 10:30:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • d2beca95dc Make docker instructions more explicit (#785) Pavol Rusnak 2023-04-06 08:56:58 +02:00
  • fa305a5d93 ggml : multi-thread ggml_rope() (~3-4 times faster on M1) (#781) Georgi Gerganov 2023-04-05 22:11:03 +03:00
  • eeaa7b0492 ggml : multi-thread ggml_rope() (~3-4 times faster on M1) (#781) Georgi Gerganov 2023-04-05 22:11:03 +03:00
  • bfd2e09522 ggml, llama : avoid heavy V transpose + improvements (#775) Georgi Gerganov 2023-04-05 22:07:33 +03:00
  • 986b6ce9f9 ggml, llama : avoid heavy V transpose + improvements (#775) Georgi Gerganov 2023-04-05 22:07:33 +03:00
  • 0470adafd0 Update README.md Georgi Gerganov 2023-04-05 19:54:30 +03:00
  • 3416298929 Update README.md Georgi Gerganov 2023-04-05 19:54:30 +03:00
  • 0049e73e0e llama : define non-positive top_k; top_k range check (#779) Ivan Stepanov 2023-04-05 19:20:05 +03:00
  • 5a8c4f6240 llama : define non-positive top_k; top_k range check (#779) Ivan Stepanov 2023-04-05 19:20:05 +03:00
  • d0ba65021b miku.sh : add executable bit (#780) at8u 2023-04-05 15:59:13 +00:00
  • ff05d05c96 miku.sh : add executable bit (#780) at8u 2023-04-05 15:59:13 +00:00
  • 94da8dfdaf media : add logos and banners Georgi Gerganov 2023-04-05 18:58:06 +03:00
  • 62b3e81aae media : add logos and banners Georgi Gerganov 2023-04-05 18:58:06 +03:00
  • a19b5cee08 readme : change logo + add bindings + add uis + add wiki Georgi Gerganov 2023-04-05 18:56:20 +03:00
  • 8d10406d6e readme : change logo + add bindings + add uis + add wiki Georgi Gerganov 2023-04-05 18:56:20 +03:00
  • 20a21e3cbf zig : add build.zig (#773) iacore 2023-04-05 15:06:02 +00:00
  • ed1c214e66 zig : add build.zig (#773) iacore 2023-04-05 15:06:02 +00:00
  • 114a713540 make : missing host optimizations in CXXFLAGS (#763) Ivan Stepanov 2023-04-05 17:38:37 +03:00
  • 0c44427df1 make : missing host optimizations in CXXFLAGS (#763) Ivan Stepanov 2023-04-05 17:38:37 +03:00
  • 5cdd9ef43f readme : update with CMake and windows example (#748) Adithya Balaji 2023-04-05 16:36:12 +02:00
  • 594cc95fab readme : update with CMake and windows example (#748) Adithya Balaji 2023-04-05 16:36:12 +02:00
  • 06bf2b5f86 examples : add Miku.sh (#724) at8u 2023-04-05 14:32:42 +00:00
  • 88ed5761b8 examples : add Miku.sh (#724) at8u 2023-04-05 14:32:42 +00:00
  • 54aaf78743 Add Accelerate/BLAS when using Swift (#765) Andrew Duffy 2023-04-05 11:44:24 +01:00
  • 58c438cf7d Add Accelerate/BLAS when using Swift (#765) Andrew Duffy 2023-04-05 11:44:24 +01:00
  • c94c876bb6 Windows: reactive sigint handler after each Ctrl-C (#736) mgroeber9110 2023-04-03 18:00:55 +02:00
  • 53dbba7695 Windows: reactive sigint handler after each Ctrl-C (#736) mgroeber9110 2023-04-03 18:00:55 +02:00
  • 10d8b9e8b9 10+% performance improvement of ggml_vec_dot_q4_0 on AVX2 (#654) SebastianApel 2023-04-03 09:52:28 +02:00
  • 437e77855a 10+% performance improvement of ggml_vec_dot_q4_0 on AVX2 (#654) SebastianApel 2023-04-03 09:52:28 +02:00
  • c59dd952e4 Define non-positive temperature behavior (#720) Ivan Stepanov 2023-04-03 03:19:04 +03:00
  • cd7fa95690 Define non-positive temperature behavior (#720) Ivan Stepanov 2023-04-03 03:19:04 +03:00
  • dd873d495a Remove torch GPU dependencies from the Docker.full image (#665) bsilvereagle 2023-04-02 15:13:03 -07:00
  • a0c0516416 Remove torch GPU dependencies from the Docker.full image (#665) bsilvereagle 2023-04-02 15:13:03 -07:00
  • 01e2261e5f Add a missing step to the gpt4all instructions (#690) Thatcher Chamberlin 2023-04-02 06:48:57 -04:00
  • d8d4e865cd Add a missing step to the gpt4all instructions (#690) Thatcher Chamberlin 2023-04-02 06:48:57 -04:00
  • 35405e6856 Added api for getting/setting the kv_cache (#685) Christian Falch 2023-04-02 12:23:04 +02:00
  • e986f94829 Added api for getting/setting the kv_cache (#685) Christian Falch 2023-04-02 12:23:04 +02:00
  • b61594c857 ggml : change ne to int64_t (#626) Marian Cepok 2023-04-02 12:21:31 +02:00
  • c0bb1d3ce2 ggml : change ne to int64_t (#626) Marian Cepok 2023-04-02 12:21:31 +02:00
  • 727a6059fe examples : add gpt4all script (#658) Leonardo Neumann 2023-04-02 04:56:20 -03:00
  • 6e7801d08d examples : add gpt4all script (#658) Leonardo Neumann 2023-04-02 04:56:20 -03:00
  • aa6766c975 llama : do not allocate KV cache for "vocab_only == true" (#682) Stephan Walter 2023-04-02 07:18:53 +00:00
  • 81040f10aa llama : do not allocate KV cache for "vocab_only == true" (#682) Stephan Walter 2023-04-02 07:18:53 +00:00
  • 6285e389b3 make : use -march=native -mtune=native on x86 (#609) Fabian 2023-04-02 09:17:05 +02:00
  • c4f89d8d73 make : use -march=native -mtune=native on x86 (#609) Fabian 2023-04-02 09:17:05 +02:00
  • 5b61d03180 fix default params for examples/main (#697) Murilo Santana 2023-04-01 23:41:12 -03:00
  • 5b70e7de4c fix default params for examples/main (#697) Murilo Santana 2023-04-01 23:41:12 -03:00
  • bb36bca0f8 py: huggingface -> Hugging Face (#686) Ikko Eltociear Ashimine 2023-04-02 01:38:18 +09:00
  • a717cba844 py: huggingface -> Hugging Face (#686) Ikko Eltociear Ashimine 2023-04-02 01:38:18 +09:00
  • 34977d15c2 readme: replace termux links with homepage, play store is deprecated (#680) rimoliga 2023-04-01 11:57:30 -03:00
  • d0a7f742e7 readme: replace termux links with homepage, play store is deprecated (#680) rimoliga 2023-04-01 11:57:30 -03:00
  • 8060cfc838 Show error message when -f fails Slaren 2023-03-31 20:03:48 +02:00
  • 0d054e292e Show error message when -f fails Slaren 2023-03-31 20:03:48 +02:00
  • f7ea9fa785 Enable -std= for cmake builds, fix warnings (#598) Stephan Walter 2023-03-31 19:19:16 +00:00
  • 3525899277 Enable -std= for cmake builds, fix warnings (#598) Stephan Walter 2023-03-31 19:19:16 +00:00
  • 770361c7a7 Optimize AVX2 ggml_vec_dot_q4_0 (#642) slaren 2023-03-31 17:55:52 +02:00
  • 1d08882afa Optimize AVX2 ggml_vec_dot_q4_0 (#642) slaren 2023-03-31 17:55:52 +02:00
  • f49b853100 Add AVX acceleration (#617) perserk 2023-03-31 16:55:44 +05:00
  • 02c5b27e91 Add AVX acceleration (#617) perserk 2023-03-31 16:55:44 +05:00
  • 6cdc182e32 py : cleanup the code Pavol Rusnak 2023-03-29 21:31:24 +02:00
  • cbef542879 py : cleanup the code Pavol Rusnak 2023-03-29 21:31:24 +02:00
  • e88a8002b5 drop quantize.py (now that models are using a single file) Pavol Rusnak 2023-03-31 00:52:06 +02:00
  • 9733104be5 drop quantize.py (now that models are using a single file) Pavol Rusnak 2023-03-31 00:52:06 +02:00
  • e19e304480 readme : update supported models Georgi Gerganov 2023-03-30 22:31:54 +03:00
  • 3df890aef4 readme : update supported models Georgi Gerganov 2023-03-30 22:31:54 +03:00
  • 45f44d8945 Introduce GGML migration tool for new file format Justine Tunney 2023-03-30 05:42:56 -07:00
  • ee0c40dd6d Introduce GGML migration tool for new file format Justine Tunney 2023-03-30 05:42:56 -07:00
  • 1eaba2c35b Ensure --mlock works properly with mmap() support Justine Tunney 2023-03-30 01:53:36 -07:00
  • 6f23ba5ee2 Ensure --mlock works properly with mmap() support Justine Tunney 2023-03-30 01:53:36 -07:00
  • bb3e5452e9 Make loading weights 10-100x faster Justine Tunney 2023-03-29 13:51:37 -07:00
  • 78ca9838ee Make loading weights 10-100x faster Justine Tunney 2023-03-29 13:51:37 -07:00
  • 81c13359bb Initial windows support (untested) Slaren 2023-03-29 22:22:36 +02:00
  • a017390358 Initial windows support (untested) Slaren 2023-03-29 22:22:36 +02:00
  • c2aa32e62f Always initialize mm_addr and mm_length in llama_model Slaren 2023-03-29 08:53:14 +02:00
  • ac184d5147 Always initialize mm_addr and mm_length in llama_model Slaren 2023-03-29 08:53:14 +02:00
  • 7697211099 Unmap the file in llama_free Slaren 2023-03-29 08:31:26 +02:00
  • 276e5b7811 Unmap the file in llama_free Slaren 2023-03-29 08:31:26 +02:00
  • 4ccd1fa7b4 Make mmap_file static Slaren 2023-03-29 06:18:18 +02:00
  • d68c5dc435 Make mmap_file static Slaren 2023-03-29 06:18:18 +02:00
  • ee1eb8aab0 Fix ggml_init_params in quantize Slaren 2023-03-29 05:38:57 +02:00
  • 64bde3ffd4 Fix ggml_init_params in quantize Slaren 2023-03-29 05:38:57 +02:00
  • 4608b1ee54 Add mmap support for model files Slaren 2023-03-29 02:03:43 +02:00
  • c03ae8dca1 Add mmap support for model files Slaren 2023-03-29 02:03:43 +02:00
  • f27e27c590 cmake : properly invoke CTest (#629) Stephan Walter 2023-03-30 17:56:59 +00:00
  • 3bcc129ba8 cmake : properly invoke CTest (#629) Stephan Walter 2023-03-30 17:56:59 +00:00
  • 3b78ca3c81 Remove unused variable (#607) Casey Primozic 2023-03-30 10:53:35 -07:00
  • a4755cf288 Remove unused variable (#607) Casey Primozic 2023-03-30 10:53:35 -07:00
  • dc396d9386 make : fix darwin f16c flags check (#615) david raistrick 2023-03-30 13:34:45 -04:00
  • 1f0414feec make : fix darwin f16c flags check (#615) david raistrick 2023-03-30 13:34:45 -04:00
  • 46bc56c86e ggml : fix NEON signs (close #620, #622) Georgi Gerganov 2023-03-30 20:27:32 +03:00
  • 77efdf5a50 ggml : fix NEON signs (close #620, #622) Georgi Gerganov 2023-03-30 20:27:32 +03:00
  • c7a5aebde4 Fix GGML_F32Cx8_STORE in AVX without F16C path (#619) slaren 2023-03-30 11:16:30 +02:00
  • ed3c680bcd Fix GGML_F32Cx8_STORE in AVX without F16C path (#619) slaren 2023-03-30 11:16:30 +02:00
  • 357f21576e ci : re-enable AVX512 testing (Windows-MSVC) (#584) anzz1 2023-03-29 23:44:39 +03:00
  • 9cbc404ba6 ci : re-enable AVX512 testing (Windows-MSVC) (#584) anzz1 2023-03-29 23:44:39 +03:00
  • 7639a7c89c ggml : init time on first ggml_init() call Georgi Gerganov 2023-03-29 22:15:34 +03:00
  • b51c717d5c ggml : init time on first ggml_init() call Georgi Gerganov 2023-03-29 22:15:34 +03:00
  • ed1554989a llama : fix compile warnings when reading the vocab Georgi Gerganov 2023-03-29 22:13:12 +03:00
  • 0ba76c1e73 llama : fix compile warnings when reading the vocab Georgi Gerganov 2023-03-29 22:13:12 +03:00
  • 169c724830 ggml : add ARM_NEON dequantize_row_q4_1() Georgi Gerganov 2023-03-29 22:10:01 +03:00