ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-28 00:54:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 6c5629d4d2 add #include <string> to unicode.h (#5051) bobqianic 2024-01-21 15:17:35 +00:00
  • 9a6b77d595 Add ability to evauate multiple choice tasks (#5047) Kawrakow 2024-01-21 14:42:44 +02:00
  • 7dcbe39d36 Add ability to evauate multiple choice tasks (#5047) Kawrakow 2024-01-21 14:42:44 +02:00
  • cb2341a665 Slightly faster imatrix (#5050) Kawrakow 2024-01-21 08:01:20 +02:00
  • 726c0fa9a2 Slightly faster imatrix (#5050) Kawrakow 2024-01-21 08:01:20 +02:00
  • fb68f21765 flake.lock: Update (#5054) Georgi Gerganov 2024-01-21 05:17:27 +02:00
  • 942c0107a7 flake.lock: Update (#5054) Georgi Gerganov 2024-01-21 05:17:27 +02:00
  • 4461e32e36 convert : partially revert PR #4818 (#5041) Jared Van Bortel 2024-01-20 18:14:18 -05:00
  • b43ebde3b0 convert : partially revert PR #4818 (#5041) Jared Van Bortel 2024-01-20 18:14:18 -05:00
  • 6cac3ffdbf perplexity : fix MSVC build after #5020 (#5043) Jared Van Bortel 2024-01-20 10:08:08 -05:00
  • 97c1549808 perplexity : fix MSVC build after #5020 (#5043) Jared Van Bortel 2024-01-20 10:08:08 -05:00
  • ec252dfbb1 llama : run all KQV ops on the CPU with no KV offload (#5049) slaren 2024-01-20 16:05:49 +01:00
  • 6df465a91d llama : run all KQV ops on the CPU with no KV offload (#5049) slaren 2024-01-20 16:05:49 +01:00
  • 0a093b1cbb cmake : add support for ccache (#5002) Herman Semenov 2024-01-20 08:11:31 +00:00
  • 77bc1bbd05 cmake : add support for ccache (#5002) Herman Semenov 2024-01-20 08:11:31 +00:00
  • 0891e26f16 Add a dart/flutter binding to README.md (#4882) adel boussaken 2024-01-20 09:05:43 +01:00
  • 48e2b13372 Add a dart/flutter binding to README.md (#4882) adel boussaken 2024-01-20 09:05:43 +01:00
  • b525ea981f cuda : fix compile error in jetson platform (#4975) Kylin 2024-01-20 15:01:46 +08:00
  • cca894f16a cuda : fix compile error in jetson platform (#4975) Kylin 2024-01-20 15:01:46 +08:00
  • 48d3127e56 finetune : fix ggml_allocr lifetimes (tmp workaround) (#5033) Uzo Nweke 2024-01-19 13:20:50 -05:00
  • 381ee19572 finetune : fix ggml_allocr lifetimes (tmp workaround) (#5033) Uzo Nweke 2024-01-19 13:20:50 -05:00
  • e4b9f2c841 imatrix : add README.md Georgi Gerganov 2024-01-19 15:24:47 +02:00
  • a5cacb22b2 imatrix : add README.md Georgi Gerganov 2024-01-19 15:24:47 +02:00
  • fc798e7035 llama : support upcoming Qwen2 (#5037) Shijie 2024-01-19 19:53:13 +08:00
  • 9b75cb2b3c llama : support upcoming Qwen2 (#5037) Shijie 2024-01-19 19:53:13 +08:00
  • 538e806ec1 py : fix flake8 lint Georgi Gerganov 2024-01-19 13:52:22 +02:00
  • de9a147df1 py : fix flake8 lint Georgi Gerganov 2024-01-19 13:52:22 +02:00
  • 8eea9170ff winogrande: evaluate log-probs in parallel (#5036) Kawrakow 2024-01-19 11:39:11 +02:00
  • 7051aacfac winogrande: evaluate log-probs in parallel (#5036) Kawrakow 2024-01-19 11:39:11 +02:00
  • 234f8b0a95 llama : add CodeShell support (#5016) chiranko 2024-01-19 17:07:27 +08:00
  • 2b3b999cac llama : add CodeShell support (#5016) chiranko 2024-01-19 17:07:27 +08:00
  • cdf1a689c1 perplexity: avoid unnecessary alloocations and logit copies (#5035) Kawrakow 2024-01-19 11:02:39 +02:00
  • 993fba8180 perplexity: avoid unnecessary alloocations and logit copies (#5035) Kawrakow 2024-01-19 11:02:39 +02:00
  • 49f0f9a5be perplexity : faster Winogrande via batching (#5024) Georgi Gerganov 2024-01-19 10:45:06 +02:00
  • 8b20858e5e perplexity : faster Winogrande via batching (#5024) Georgi Gerganov 2024-01-19 10:45:06 +02:00
  • 8ed186203c llama : fix falcon arch for tied output embeddings (#4978) John 2024-01-18 23:12:15 +01:00
  • 57e2a7a52a llama : fix falcon arch for tied output embeddings (#4978) John 2024-01-18 23:12:15 +01:00
  • 8a4d0e3cf5 cmake : add ggml public headers (#5011) Georgi Gerganov 2024-01-18 23:36:07 +02:00
  • 9b6ea4263a cmake : add ggml public headers (#5011) Georgi Gerganov 2024-01-18 23:36:07 +02:00
  • 4d5cc65823 server : defer tasks when "slot unavailable" (#5018) Xuan Son Nguyen 2024-01-18 21:33:05 +01:00
  • 821f0a271e server : defer tasks when "slot unavailable" (#5018) Xuan Son Nguyen 2024-01-18 21:33:05 +01:00
  • 8d779e531e llama : fix mlock with no-mmap with Metal (#5025) slaren 2024-01-18 21:12:15 +01:00
  • 96d7f56d29 llama : fix mlock with no-mmap with Metal (#5025) slaren 2024-01-18 21:12:15 +01:00
  • d23cd25dd0 imatrix : fix assert for src0 non-cont check Georgi Gerganov 2024-01-18 21:45:51 +02:00
  • 2d5419d08a imatrix : fix assert for src0 non-cont check Georgi Gerganov 2024-01-18 21:45:51 +02:00
  • 82b820d593 perplexity : fix winogrande N tasks option Georgi Gerganov 2024-01-18 20:49:00 +02:00
  • d391ae9b49 perplexity : fix winogrande N tasks option Georgi Gerganov 2024-01-18 20:49:00 +02:00
  • 8e6a95c27e scripts : add get-winogrande.sh Georgi Gerganov 2024-01-18 20:45:39 +02:00
  • e9240cdfa0 scripts : add get-winogrande.sh Georgi Gerganov 2024-01-18 20:45:39 +02:00
  • 521f3bafe5 convert.py : fix llama/llama2 conversion due to vocab_size=-1 (#5019) David Sommers 2024-01-18 12:20:59 -05:00
  • b46757735d convert.py : fix llama/llama2 conversion due to vocab_size=-1 (#5019) David Sommers 2024-01-18 12:20:59 -05:00
  • c7bb8e340a HellaSwag: speed up by parallelizing log-prob evaluation (#5020) Kawrakow 2024-01-18 19:18:21 +02:00
  • 3e945cc1e9 HellaSwag: speed up by parallelizing log-prob evaluation (#5020) Kawrakow 2024-01-18 19:18:21 +02:00
  • f46c1ab2da perplexity : faster HellaSwag via batching (#5017) Georgi Gerganov 2024-01-18 15:33:01 +02:00
  • ad19812cda perplexity : faster HellaSwag via batching (#5017) Georgi Gerganov 2024-01-18 15:33:01 +02:00
  • cc90bc53e3 Add Winogrande evaluation (#5015) Kawrakow 2024-01-18 13:46:27 +02:00
  • 682986a08e Add Winogrande evaluation (#5015) Kawrakow 2024-01-18 13:46:27 +02:00
  • 98642b6cb3 scritps : add helper script to get hellaswag data in txt format Georgi Gerganov 2024-01-18 11:44:49 +02:00
  • dcad445d0c scritps : add helper script to get hellaswag data in txt format Georgi Gerganov 2024-01-18 11:44:49 +02:00
  • d3612eb69a metal : fix memory leak, dangling pointer and unused autorel (#5007) Paul Tsochantaris 2024-01-18 08:47:24 +00:00
  • 1e605f4102 metal : fix memory leak, dangling pointer and unused autorel (#5007) Paul Tsochantaris 2024-01-18 08:47:24 +00:00
  • af72b6c82d sync : ggml Georgi Gerganov 2024-01-17 20:54:50 +02:00
  • 6b6916b215 sync : ggml Georgi Gerganov 2024-01-17 20:54:50 +02:00
  • 4e61593d70 ggml : add IQ2 to test-backend-ops + refactoring (#4990) Georgi Gerganov 2024-01-17 18:54:56 +02:00
  • 38566680cd ggml : add IQ2 to test-backend-ops + refactoring (#4990) Georgi Gerganov 2024-01-17 18:54:56 +02:00
  • 2369070475 imatrix : offload to GPU support (#4957) Georgi Gerganov 2024-01-17 18:46:30 +02:00
  • ba69bbc84c imatrix : offload to GPU support (#4957) Georgi Gerganov 2024-01-17 18:46:30 +02:00
  • 8eb82749e5 backend : add eval callback (#4935) Georgi Gerganov 2024-01-17 18:39:41 +02:00
  • 44a1a4a41a backend : add eval callback (#4935) Georgi Gerganov 2024-01-17 18:39:41 +02:00
  • 26ec39bca0 metal : create autorelease pool during library build (#4970) Georgi Gerganov 2024-01-17 18:38:39 +02:00
  • c918fe8dca metal : create autorelease pool during library build (#4970) Georgi Gerganov 2024-01-17 18:38:39 +02:00
  • d1677a54cf py : fix whitespace Georgi Gerganov 2024-01-17 18:37:36 +02:00
  • 0f83e727af py : fix whitespace Georgi Gerganov 2024-01-17 18:37:36 +02:00
  • 1fd018a0f1 py : fix missing added_tokens_dict for SPM and BPE vocabs (#4971) Georgi Gerganov 2024-01-17 15:45:03 +02:00
  • 4f4bf35f46 py : fix missing added_tokens_dict for SPM and BPE vocabs (#4971) Georgi Gerganov 2024-01-17 15:45:03 +02:00
  • b55a3eb734 llama : use Q4_K for attn_v for Q2_K_S when n_gqa >= 4 (#4996) Kawrakow 2024-01-17 12:36:37 +02:00
  • 2b3a665d39 llama : use Q4_K for attn_v for Q2_K_S when n_gqa >= 4 (#4996) Kawrakow 2024-01-17 12:36:37 +02:00
  • c833da5734 metal : remove unnecessary nil check (#4986) Paul Tsochantaris 2024-01-17 08:07:24 +00:00
  • 7563293665 metal : remove unnecessary nil check (#4986) Paul Tsochantaris 2024-01-17 08:07:24 +00:00
  • 2ea277255a llama : fix copy/paste error in llama_sampling_params comment (#4994) David Renshaw 2024-01-17 02:17:50 -05:00
  • f46c0c1b0e llama : fix copy/paste error in llama_sampling_params comment (#4994) David Renshaw 2024-01-17 02:17:50 -05:00
  • d0cfdea56b py : remove unnecessary hasattr (#4903) Georgi Gerganov 2024-01-16 20:59:31 +02:00
  • 5c99960901 py : remove unnecessary hasattr (#4903) Georgi Gerganov 2024-01-16 20:59:31 +02:00
  • 8caa88c9e3 nix: remove nixConfig from flake.nix (#4984) Philip Taron 2024-01-16 09:56:21 -08:00
  • bee938da74 nix: remove nixConfig from flake.nix (#4984) Philip Taron 2024-01-16 09:56:21 -08:00
  • 0001889453 finetune : add training data file to log message (#4979) Daniel Bevenius 2024-01-16 18:54:24 +01:00
  • cec8a48470 finetune : add training data file to log message (#4979) Daniel Bevenius 2024-01-16 18:54:24 +01:00
  • 5e9e1d50d4 ggml : importance matrix support for legacy quants (#4969) Kawrakow 2024-01-16 19:51:26 +02:00
  • 334a835a1c ggml : importance matrix support for legacy quants (#4969) Kawrakow 2024-01-16 19:51:26 +02:00
  • 09e6d92a82 examples : add complete parallel function calling example (#4974) Maximilian Winter 2024-01-16 18:41:42 +01:00
  • 4feb4b33ee examples : add complete parallel function calling example (#4974) Maximilian Winter 2024-01-16 18:41:42 +01:00
  • f985a114ca perplexity : fix kv cache handling for hellaswag (#4981) Georgi Gerganov 2024-01-16 19:34:54 +02:00
  • 959ef0c0df perplexity : fix kv cache handling for hellaswag (#4981) Georgi Gerganov 2024-01-16 19:34:54 +02:00
  • e27477029f flake.lock: update flake-parts, flake-parts/nixpkgs-lib, and nixpkgs (#4920) Georgi Gerganov 2024-01-16 19:13:54 +02:00
  • c37b3474e6 flake.lock: update flake-parts, flake-parts/nixpkgs-lib, and nixpkgs (#4920) Georgi Gerganov 2024-01-16 19:13:54 +02:00
  • e412985860 metal : localized logic in ggml_metal_graph_compute (#4924) Paul Tsochantaris 2024-01-16 17:05:19 +00:00
  • 158f8c9e21 metal : localized logic in ggml_metal_graph_compute (#4924) Paul Tsochantaris 2024-01-16 17:05:19 +00:00
  • 0641f5e160 android : introduce starter project example (#4926) Neuman Vong 2024-01-17 00:47:34 +11:00
  • 862f5e41ab android : introduce starter project example (#4926) Neuman Vong 2024-01-17 00:47:34 +11:00
  • 7d32fe7044 metal : replace loop of dispatch_async with dispatch_apply (#4934) Alex Azarov 2024-01-16 14:41:27 +01:00