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

  • f4d277ae17 main : alternative instruct mode (Vicuna support, etc.) (#863) Tomáš Pazdiora 2023-04-14 17:19:17 +02:00
  • 0c6e3a6e6f ggml : add unary and binary map operations (#874) Kerfuffle 2023-04-14 08:43:55 -06:00
  • c9a59b70a5 ggml : add unary and binary map operations (#874) Kerfuffle 2023-04-14 08:43:55 -06:00
  • 147f0b769c py : cleanup dependencies (#962) Pavol Rusnak 2023-04-14 15:37:11 +02:00
  • a32f7acc9f py : cleanup dependencies (#962) Pavol Rusnak 2023-04-14 15:37:11 +02:00
  • dd9b2450a6 py : fix flake8 and isort nitpicks (#960) Pavol Rusnak 2023-04-14 14:23:21 +02:00
  • 43ffdefb74 py : fix flake8 and isort nitpicks (#960) Pavol Rusnak 2023-04-14 14:23:21 +02:00
  • 64179095f2 ggml : minor Georgi Gerganov 2023-04-14 13:31:29 +03:00
  • 1623a6e9b4 ggml : minor Georgi Gerganov 2023-04-14 13:31:29 +03:00
  • ebc6e99a4a ggml : always allocate buffers with size multiple of GGML_MEM_ALIGN Georgi Gerganov 2023-04-14 13:31:15 +03:00
  • c14e0d2f23 ggml : always allocate buffers with size multiple of GGML_MEM_ALIGN Georgi Gerganov 2023-04-14 13:31:15 +03:00
  • 3573ed90b8 py : new conversion script (#545) comex 2023-04-14 00:03:03 -07:00
  • 723dac55fa py : new conversion script (#545) comex 2023-04-14 00:03:03 -07:00
  • d7f330d1c4 ggml : fix q4_1 dot product types Georgi Gerganov 2023-04-14 09:45:42 +03:00
  • 0f07cacb05 ggml : fix q4_1 dot product types Georgi Gerganov 2023-04-14 09:45:42 +03:00
  • e0dbf8218f ggml : optimize rope function to avoid call powf in the tight loop (#807) Howard Su 2023-04-14 14:24:52 +08:00
  • c5d70f5c9e ggml : optimize rope function to avoid call powf in the tight loop (#807) Howard Su 2023-04-14 14:24:52 +08:00
  • 5d44c13ecb perplexity : add support for batch size to --perplexity (#407) Gary Linscott 2023-04-13 14:50:42 -07:00
  • be87b6ed20 perplexity : add support for batch size to --perplexity (#407) Gary Linscott 2023-04-13 14:50:42 -07:00
  • 83af18bc18 common : remove unnecessary includes (#947) CRD716 2023-04-13 10:39:25 -05:00
  • 0e07e6a839 common : remove unnecessary includes (#947) CRD716 2023-04-13 10:39:25 -05:00
  • faf1c350cb ggml : add GGML_DEFAULT_N_THREADS Georgi Gerganov 2023-04-13 18:36:40 +03:00
  • a3a2a0eda8 ggml : add GGML_DEFAULT_N_THREADS Georgi Gerganov 2023-04-13 18:36:40 +03:00
  • 609adf4f48 ggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit ARM support (#900) Georgi Gerganov 2023-04-13 18:32:36 +03:00
  • d990e3fffc ggml : speed-up ggml_vec_dot_q4_1() ARM_NEON + 32-bit ARM support (#900) Georgi Gerganov 2023-04-13 18:32:36 +03:00
  • d9dff86873 llama : merge llama_internal.h into llama.h Georgi Gerganov 2023-04-13 18:04:45 +03:00
  • 9190e8eac8 llama : merge llama_internal.h into llama.h Georgi Gerganov 2023-04-13 18:04:45 +03:00
  • 25df0f1555 gitignore : benchmark Georgi Gerganov 2023-04-13 18:01:22 +03:00
  • c85980acd0 gitignore : benchmark Georgi Gerganov 2023-04-13 18:01:22 +03:00
  • 2bf3e1346e ggml : optimize non-SIMD Q4_0 vector dot product (#703) Stephan Walter 2023-04-13 14:59:50 +00:00
  • 6232f2d7fd ggml : optimize non-SIMD Q4_0 vector dot product (#703) Stephan Walter 2023-04-13 14:59:50 +00:00
  • 3a62b13f43 ggml : introduce GGML_ALIGNED_MALLOC/GGML_ALIGNED_FREE macros (#884) Pavol Rusnak 2023-04-13 16:08:32 +02:00
  • 6c248707f5 ggml : introduce GGML_ALIGNED_MALLOC/GGML_ALIGNED_FREE macros (#884) Pavol Rusnak 2023-04-13 16:08:32 +02:00
  • 62addfa732 fix whitespace (#944) CRD716 2023-04-13 09:03:57 -05:00
  • 8cda5c981d fix whitespace (#944) CRD716 2023-04-13 09:03:57 -05:00
  • d74ce11c25 readme : remove python 3.10 warning (#929) CRD716 2023-04-13 08:59:53 -05:00
  • ec29272175 readme : remove python 3.10 warning (#929) CRD716 2023-04-13 08:59:53 -05:00
  • c720fa4877 readme : llama node binding (#911) Genkagaku.GPT 2023-04-13 21:54:27 +08:00
  • 7e941b95eb readme : llama node binding (#911) Genkagaku.GPT 2023-04-13 21:54:27 +08:00
  • 787a6000c4 flake.nix: add all binaries from bin (#848) Pavol Rusnak 2023-04-13 15:49:05 +02:00
  • c729ff730a flake.nix: add all binaries from bin (#848) Pavol Rusnak 2023-04-13 15:49:05 +02:00
  • b9a4538eaa zig : update build.zig (#872) Judd 2023-04-13 21:43:22 +08:00
  • 4579af95e8 zig : update build.zig (#872) Judd 2023-04-13 21:43:22 +08:00
  • bcc5569f59 ggml : update cblas_sgemm columns var to be more reasonable (#838) Vladimir 2023-04-13 15:24:30 +02:00
  • 8c3ffc2f04 ggml : update cblas_sgemm columns var to be more reasonable (#838) Vladimir 2023-04-13 15:24:30 +02:00
  • 9a5c5d1e92 examples : add -n to alpaca and gpt4all scripts (#706) niansa/tuxifan 2023-04-13 15:03:39 +02:00
  • 107980d970 examples : add -n to alpaca and gpt4all scripts (#706) niansa/tuxifan 2023-04-13 15:03:39 +02:00
  • aa044c07c5 cmake : add explicit F16C option (x86) (#576) anzz1 2023-04-13 15:48:21 +03:00
  • 585d91a156 cmake : add explicit F16C option (x86) (#576) anzz1 2023-04-13 15:48:21 +03:00
  • 45a86141bb benchmark : add tool for timing q4_0 matrix multiplication (#653) SebastianApel 2023-04-13 14:46:23 +02:00
  • 95ea26f6e9 benchmark : add tool for timing q4_0 matrix multiplication (#653) SebastianApel 2023-04-13 14:46:23 +02:00
  • d8bae1b2c2 do not force the prompt file to end with a new line (#908) Pavol Rusnak 2023-04-13 11:33:16 +02:00
  • 82d146df9b do not force the prompt file to end with a new line (#908) Pavol Rusnak 2023-04-13 11:33:16 +02:00
  • 2ed5c65183 Don't crash on ftype (formerly f16) == 4 (#917) Stephan Walter 2023-04-12 15:06:16 +00:00
  • e7f6997f89 Don't crash on ftype (formerly f16) == 4 (#917) Stephan Walter 2023-04-12 15:06:16 +00:00
  • be7082caef readme : change "GPU support" link to discussion Georgi Gerganov 2023-04-12 14:48:57 +03:00
  • f76cb3a34d readme : change "GPU support" link to discussion Georgi Gerganov 2023-04-12 14:48:57 +03:00
  • 9b68f0ee36 readme : update hot topics with link to "GPU support" issue Georgi Gerganov 2023-04-12 14:31:12 +03:00
  • 782438070f readme : update hot topics with link to "GPU support" issue Georgi Gerganov 2023-04-12 14:31:12 +03:00
  • e610019c01 readme: link to sha256sums file (#902) Nicolai Weitkemper 2023-04-12 08:46:20 +02:00
  • 4dbbd40750 readme: link to sha256sums file (#902) Nicolai Weitkemper 2023-04-12 08:46:20 +02:00
  • e4d3b4b251 Fix whitespace, add .editorconfig, add GitHub workflow (#883) Pavol Rusnak 2023-04-11 21:45:44 +02:00
  • 8b679987cd Fix whitespace, add .editorconfig, add GitHub workflow (#883) Pavol Rusnak 2023-04-11 21:45:44 +02:00
  • c8296315db Add enum llama_ftype, sync ggml_type to model files (#709) Stephan Walter 2023-04-11 15:03:51 +00:00
  • 3e6e70d8e8 Add enum llama_ftype, sync ggml_type to model files (#709) Stephan Walter 2023-04-11 15:03:51 +00:00
  • 74ad81e8a0 Windows fixes (#890) comex 2023-04-11 06:19:54 -07:00
  • 2663d2c678 Windows fixes (#890) comex 2023-04-11 06:19:54 -07:00
  • 4b0adc70d7 Add BAIR's Koala to supported models (#877) qouoq 2023-04-11 04:41:53 +08:00
  • a0caa34b16 Add BAIR's Koala to supported models (#877) qouoq 2023-04-11 04:41:53 +08:00
  • 9c28c0bbd9 ggml : fix WASM build Georgi Gerganov 2023-04-10 23:20:01 +03:00
  • 461ba9e66e ggml : fix WASM build Georgi Gerganov 2023-04-10 23:20:01 +03:00
  • 2dbbb0ab85 ggml : add ggml_cont() + optimize ggml_cpy() for contiguous dst Georgi Gerganov 2023-04-10 22:40:28 +03:00
  • c3ac702e5e ggml : add ggml_cont() + optimize ggml_cpy() for contiguous dst Georgi Gerganov 2023-04-10 22:40:28 +03:00
  • 1371cdbec8 ggml : remove trailing whitespaces Georgi Gerganov 2023-04-10 19:32:45 +03:00
  • 9d634ef452 ggml : remove trailing whitespaces Georgi Gerganov 2023-04-10 19:32:45 +03:00
  • e3a4645406 Simplify to include lower-case windows.h always, fix compile on mingw32 (#747) Marco Matthies 2023-04-10 19:57:59 +02:00
  • d9a239c410 Simplify to include lower-case windows.h always, fix compile on mingw32 (#747) Marco Matthies 2023-04-10 19:57:59 +02:00
  • caa39e53b1 ggml : fix quantize_row_q4_1() ARM_NEON (close #876) Georgi Gerganov 2023-04-10 19:29:48 +03:00
  • 684da25926 ggml : fix quantize_row_q4_1() ARM_NEON (close #876) Georgi Gerganov 2023-04-10 19:29:48 +03:00
  • e6c63e305f Print model version. comex 2023-04-08 13:08:21 -07:00
  • 180b693a47 Print model version. comex 2023-04-08 13:08:21 -07:00
  • 84cfa98c43 Rewrite loading code to try to satisfy everyone: comex 2023-04-08 12:24:37 -07:00
  • f963b63afa Rewrite loading code to try to satisfy everyone: comex 2023-04-08 12:24:37 -07:00
  • ecc4a042a0 fix for windows utf-8 input (#840) Tomáš Pazdiora 2023-04-08 17:49:39 +02:00
  • aaf3b23deb fix for windows utf-8 input (#840) Tomáš Pazdiora 2023-04-08 17:49:39 +02:00
  • e0a36d1bd6 cmake should link openblas properly with -lopenblas like how it's done in the makefile (#839) eiery 2023-04-08 07:15:17 -04:00
  • f2d1c47294 cmake should link openblas properly with -lopenblas like how it's done in the makefile (#839) eiery 2023-04-08 07:15:17 -04:00
  • 7e9de8684c Add new binaries to flake.nix (#847) lon 2023-04-08 07:04:23 -03:00
  • 317fb12fbd Add new binaries to flake.nix (#847) lon 2023-04-08 07:04:23 -03:00
  • c9ffd853d5 Add quantize-stats command for testing quantization (#728) unbounded 2023-04-08 00:09:18 +02:00
  • 62cfc54f77 Add quantize-stats command for testing quantization (#728) unbounded 2023-04-08 00:09:18 +02:00
  • 7befe47794 make : add libllama.so target for llama-cpp-python (#797) bhubbb 2023-04-08 02:11:58 +10:00
  • 698f7b5d63 make : add libllama.so target for llama-cpp-python (#797) bhubbb 2023-04-08 02:11:58 +10:00
  • 3dc60db9f4 zig : don't link examples/common.cpp for non-example (#814) iacore 2023-04-07 16:05:29 +00:00
  • c1950c3431 zig : don't link examples/common.cpp for non-example (#814) iacore 2023-04-07 16:05:29 +00:00
  • 605e571c31 llama : always sort logits before nucleus sampling (#812) Ivan Stepanov 2023-04-07 19:02:12 +03:00
  • 4953e9007f llama : always sort logits before nucleus sampling (#812) Ivan Stepanov 2023-04-07 19:02:12 +03:00
  • 52fc351cd2 Do not crash when it has nothing to say. (#796) Sergey Alirzaev 2023-04-06 17:59:11 +02:00
  • cc9cee8e9e Do not crash when it has nothing to say. (#796) Sergey Alirzaev 2023-04-06 17:59:11 +02:00
  • 944d161986 Make docker instructions more explicit (#785) Pavol Rusnak 2023-04-06 08:56:58 +02:00