vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Commit graph

  • 48edda30ee
         convert : update Falcon script for new HF config (#3448) cebtenzzre 2023-10-05 15:00:34 -04:00
  • 5354916064 Merge branch 'master' of https://github.com/FSSRepo/llama.cpp FSSRepo 2023-10-05 14:45:20 -04:00
  • dc102b4493 add change system prompt on runtime, improve README FSSRepo 2023-10-05 14:36:58 -04:00
  • 9e6e714dc5 some var names, state fixes + improvement performance FSSRepo 2023-10-04 14:49:35 -04:00
  • 9a1039d9ee fix mac os ci error: string -> char* FSSRepo 2023-10-03 18:36:47 -04:00
  • 33c2a25e3f fix ci errors FSSRepo 2023-10-03 17:43:32 -04:00
  • e44cef8144 server: handle multiple completions with cam FSSRepo 2023-10-03 17:39:24 -04:00
  • bd13ea3116 add change system prompt on runtime, improve README FSSRepo 2023-10-05 14:36:58 -04:00
  • 5d259d358c Merge branch 'master' of github.com:ggerganov/llama.cpp into phillip-kravtsov/support-adept-persimmon-8b. ggml-ci Phillip Kravtsov 2023-10-05 08:08:55 -07:00
  • 2c24d67e7b Don't crash on available devices if we can't even create an instance. Adam Treat 2023-09-16 12:17:29 -04:00
  • addac25293 Set the singleton to nullptr here. Adam Treat 2023-09-14 16:38:28 -04:00
  • 68aca6be08 Only use vulkan with known quant that work. Adam Treat 2023-09-14 09:58:28 -04:00
  • 4ed25b2f88 Sync from device back to host at begin of new prompt. Adam Treat 2023-09-13 20:47:40 -04:00
  • bd5f6399bb Don't try and install kompute artifacts. Adam Treat 2023-09-13 17:04:47 -04:00
  • 8bea719879 vulkan: disambiguate gpus with the same name Aaron Miller 2023-09-13 09:51:40 -07:00
  • 68cf1df6fb Throw an exception when allocation fails for vulkan. Adam Treat 2023-09-13 10:32:43 -04:00
  • beee57266f Make kompute actually include external SDK headers when requested Aaron Miller 2023-09-12 12:36:13 -07:00
  • b7e2e691d4 Completely revamp how we do object management with the vulkan backend and stop using so many static objects so we can tear down and bring up vulkan on new devices in the same runtime. Adam Treat 2023-09-12 13:04:55 -04:00
  • 45c8778b49 Switch to a dynamic dispatch table instead of linking hard against libvulkan. Adam Treat 2023-09-12 12:39:38 -04:00
  • 8563fa001f remove dynamic deps from kompute build Aaron Miller 2023-09-05 13:42:27 -07:00
  • 48a45ea435 Remove warning which fails on windows. Adam Treat 2023-08-30 14:33:31 -04:00
  • ba15dfd0be Nomic vulkan backend licensed under the Software for Open Models License (SOM), version 1.0. niansa 2023-06-22 12:58:07 +02:00
  • 45eba9369f
         build : use std::make_tuple() for compatibility with older GCC versions (#3488) b1329 Kenvix ⭐ 2023-10-06 01:16:39 +08:00
  • 57b6f02b80 Merge branch 'master' of https://github.com/ggerganov/llama.cpp Kenvix Zure 2023-10-06 00:36:57 +08:00
  • ef0fa5427b build: use std::make_tuple() for compatibility with older GCC versions Kenvix Zure 2023-10-06 00:31:16 +08:00
  • 297b7b6301 Automation pudepiedj 2023-10-05 17:30:48 +01:00
  • acec9eaaa9
         common : process escape sequences in reverse prompts (#3461) b1328 staviq 2023-10-05 18:17:29 +02:00
  • db44b469d3
         Merge branch 'ggerganov:master' into load-parallel-prompt-file pudepiedj 2023-10-05 15:43:26 +01:00
  • 325fcb75ad Remove jeopardy results file pudepiedj 2023-10-05 15:41:02 +01:00
  • 275d56e99e Update cmap-example pudepiedj 2023-10-05 15:38:21 +01:00
  • e2583cbc29 CLBlast: Fix handling of on-device tensor data b1327 shibe2 2023-10-05 15:57:03 +04:00
  • da8a09ba10 use filename as default model name Concedo 2023-10-05 22:24:20 +08:00
  • e8b8d32e86
         server : fix incorrect num_tokens_predicted (#3480) b1326 Jhen-Jie Hong 2023-10-05 09:02:55 -05:00
  • 8f3a642ec1
         swift : disable ACCELERATE_NEW_LAPACK (#3481) Jhen-Jie Hong 2023-10-05 09:00:07 -05:00
  • 0745384449
         ci : add swift build via xcodebuild (#3482) b1324 Jhen-Jie Hong 2023-10-05 08:56:21 -05:00
  • 94dd85c5f0 convert : merge Falcon-180B script into main Falcon script Cebtenzzre 2023-10-02 18:08:22 -04:00
  • 73eefdf3c6 gguf: add script for converting falcon 180B jb 2023-09-06 23:04:14 +02:00
  • a0c1ba7747 Merge branch 'concedo_experimental' of https://github.com/LostRuins/llamacpp-for-kobold into concedo_experimental Concedo 2023-10-05 21:20:21 +08:00
  • b4b5c35074 add documentation for koboldcpp Concedo 2023-10-05 21:17:36 +08:00
  • f9f4cdf3c0
         Implement basic chat/completions openai endpoint (#461) teddybear082 2023-10-05 08:13:10 -04:00
  • 7d9e3ca6e0 CLBlast: Fix handling of on-device tensor data shibe2 2023-10-05 15:57:03 +04:00
  • 380a10f8b5 Update cmap-example pudepiedj 2023-10-05 12:35:19 +01:00
  • 317d195f68 Update cmap-examples pudepiedj 2023-10-05 12:33:20 +01:00
  • 7804fe0d68 Update cmap-example pudepiedj 2023-10-05 12:31:10 +01:00
  • 9dad8b81e1 Update cmap-example pudepiedj 2023-10-05 12:23:49 +01:00
  • 73fa2deee1 Update cmap-example pudepiedj 2023-10-05 12:18:21 +01:00
  • e3c8f7bd16 Update cmap-example pudepiedj 2023-10-05 12:13:30 +01:00
  • eb939e0638 Update cmap-example pudepiedj 2023-10-05 12:04:03 +01:00
  • aea055db42 Update cmap_example pudepiedj 2023-10-05 11:52:44 +01:00
  • 1bb192fc27 Add cmap_example.cpp pudepiedj 2023-10-05 11:45:20 +01:00
  • e9aa6e9a08 Yet more LLM-questions pudepiedj 2023-10-05 11:17:28 +01:00
  • cbdfa3c2eb Merge branch 'master' of github.com:ggerganov/llama.cpp Laura 2023-10-05 10:34:35 +02:00
  • 5beb773320 Merge branch 'master' into concedo_experimental Concedo 2023-10-05 11:44:35 +08:00
  • ce065d39d0 allow drag and drop kcpps file and openwith Concedo 2023-10-05 11:38:37 +08:00
  • 67a0e8bb58
         Update README.md Bailey Chittle 2023-10-04 18:34:58 -07:00
  • 7d565c9f5e ggml metal compiles! Bailey Chittle 2023-10-04 18:10:16 -07:00
  • b5a3a89ca1 ci : add swift build via xcodebuild Jhen 2023-10-05 08:55:56 +08:00
  • 77c6e27a1f swift : disable ACCELERATE_NEW_LAPACK Jhen 2023-10-05 08:49:54 +08:00
  • 97d574b536 server : fix incorrect num_tokens_predicted Jhen 2023-10-05 08:42:14 +08:00
  • cbd632a658 some var names, state fixes + improvement performance FSSRepo 2023-10-04 14:49:35 -04:00
  • 4cffcb845a rename is_float_eq -> is_float_close Cebtenzzre 2023-10-04 14:02:14 -04:00
  • 1115a09245 Merge upstream into fix-convert-added-tokens Cebtenzzre 2023-10-04 13:17:30 -04:00
  • 5a5a71d7bd Starting gpt4all pudepiedj 2023-10-04 17:31:15 +01:00
  • 1f314784f7 server.cpp now accepts parameter -tb N, --threads-batch N Michael Coppola 2023-10-04 12:04:09 -04:00
  • bde943e6d6 minor simplification Cebtenzzre 2023-10-04 11:13:02 -04:00
  • 8394762237 Merge branch 'load-parallel-prompt-file' of https://github.com/pudepiedj/llama.cpp into load-parallel-prompt-file pudepiedj 2023-10-04 15:54:38 +01:00
  • b505cfb3bc Update LLM-questions.txt pudepiedj 2023-10-04 15:54:32 +01:00
  • f630096c35
         Merge branch 'ggerganov:master' into load-parallel-prompt-file pudepiedj 2023-10-04 15:51:41 +01:00
  • d9cb48f063 fixed code review comments l3utterfly 2023-10-04 22:23:43 +08:00
  • 019ba1dcd0
         convert : fix Baichuan2 models by using vocab size in config.json (#3299) Kerfuffle 2023-10-04 08:20:28 -06:00
  • beabc8cfb0
         readme : add project status link Georgi Gerganov 2023-10-04 16:50:44 +03:00
  • 0d152b37fe
         ggml : fix build after #3329 b1321 Georgi Gerganov 2023-10-04 16:25:41 +03:00
  • f8c90cdbaa
         llm : add Refact model (#3329) b1320 ds5t5 2023-10-04 06:23:39 -07:00
  • c736c875a2
         Merge branch 'master' into HEAD Georgi Gerganov 2023-10-04 16:20:43 +03:00
  • f93af02488
         sync : ggml (conv 1d + 2d updates, UB fixes) (#3468) b1319 Georgi Gerganov 2023-10-04 15:29:58 +03:00
  • 5b8d50574b
         tests : fix UB in test-quantize-perf Georgi Gerganov 2023-10-04 14:39:19 +03:00
  • 000c4681e4 More LLM questions pudepiedj 2023-10-04 12:38:50 +01:00
  • a02e042eb9 Corrected typo pudepiedj 2023-10-04 11:01:57 +01:00
  • 16f45c4dec updated implementation for hparam comparison to handle inf and NaN l3utterfly 2023-10-04 18:01:50 +08:00
  • f75fe38770 Improved reporting and new question files. pudepiedj 2023-10-04 10:56:30 +01:00
  • 43bbfb7a47
         ggml : fix UB in q5_0 and q5_1 quantize code Georgi Gerganov 2023-10-04 12:47:18 +03:00
  • 23277774df
         sync : ggml (conv 1d + 2d updates) Georgi Gerganov 2023-10-04 12:21:20 +03:00
  • 86c18669f0
         Merge c2c6790f9b into f72f8f22c9 Salvador E. Tropea 2023-10-04 09:34:34 +02:00
  • b805ec2899 Merge branch 'load-parallel-prompt-file' of https://github.com/pudepiedj/llama.cpp into load-parallel-prompt-file pudepiedj 2023-10-04 08:33:17 +01:00
  • 2f0181bd29 Changed .gitignore pudepiedj 2023-10-04 08:32:54 +01:00
  • bbfec95e3c
         Merge branch 'ggerganov:master' into load-parallel-prompt-file pudepiedj 2023-10-04 08:28:27 +01:00
  • 53663759b1 Remove cmake_all.sh pudepiedj 2023-10-04 08:27:10 +01:00
  • f72f8f22c9
         finetune : readme fix typo (#3465) Merrick Christensen 2023-10-04 00:33:13 -06:00
  • 47f7ebb632 adjust horde worker and debugmode Concedo 2023-10-04 14:00:07 +08:00
  • c7660ab6e6 Merge branch 'master' into concedo_experimental Concedo 2023-10-04 12:54:55 +08:00
  • eb6419ff75
         Update Finetune README.md Merrick Christensen 2023-10-03 20:54:55 -06:00
  • 55f2f2fb43 remove unnecessary copies slaren 2023-10-04 01:53:21 +02:00
  • 598e74c157 fix mac os ci error: string -> char* FSSRepo 2023-10-03 18:36:47 -04:00
  • 13916dcf6c fix ci errors FSSRepo 2023-10-03 17:43:32 -04:00
  • c3619f2d7a Process escape sequences in reverse prompts staviq 2023-10-03 23:39:58 +02:00
  • 6da48f7485 server: handle multiple completions with cam FSSRepo 2023-10-03 17:39:24 -04:00
  • c90ed9f16b Fix editorconfig formatting Phillip Kravtsov 2023-10-03 13:18:23 -07:00
  • 1364bcd712 mpt : removed ne01 + n_past == ne00 assertion from alibi (cuda/f32) and rope_shift from build_mpt Jan Ploski 2023-10-03 21:53:31 +02:00
  • 18b342dbbb remove cmake_all.sh pudepiedj 2023-10-03 20:50:02 +01:00
  • 028681835b Remove trailing whitespace pudepiedj 2023-10-03 20:40:30 +01:00