ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-26 08:04:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 9a1b6e7a11 cmake : fix typo (#7151) Jared Van Bortel 2024-05-08 19:55:32 -04:00
  • 4426e2987b cmake : fix typo (#7151) Jared Van Bortel 2024-05-08 19:55:32 -04:00
  • 282537cab8 convert-hf : save memory with lazy evaluation (#7075) compilade 2024-05-08 18:16:38 -04:00
  • f98eb31c51 convert-hf : save memory with lazy evaluation (#7075) compilade 2024-05-08 18:16:38 -04:00
  • 1570eb3501 Introduction of CUDA Graphs to LLama.cpp (#6766) agray3 2024-05-08 21:55:49 +01:00
  • bc4bba364f Introduction of CUDA Graphs to LLama.cpp (#6766) agray3 2024-05-08 21:55:49 +01:00
  • 4e708b6d16 JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143) Johannes Gäßler 2024-05-08 21:53:08 +02:00
  • c12452c7ae JSON: [key] -> .at(key), assert() -> GGML_ASSERT (#7143) Johannes Gäßler 2024-05-08 21:53:08 +02:00
  • 93ad6ba476 Revert "llava : add support for moondream vision language model (#6899)" Georgi Gerganov 2024-05-08 22:14:39 +03:00
  • 9da243b36a Revert "llava : add support for moondream vision language model (#6899)" Georgi Gerganov 2024-05-08 22:14:39 +03:00
  • eebaec0788 server : add themes + favicon (#6848) JohnnyB 2024-05-08 20:12:06 +01:00
  • bd1871fa2b server : add themes + favicon (#6848) JohnnyB 2024-05-08 20:12:06 +01:00
  • 5ba3d8201b metal : use vm_allocate instead of posix_memalign on macOS (#7078) Gilad S 2024-05-08 22:08:10 +03:00
  • 26458af1d6 metal : use vm_allocate instead of posix_memalign on macOS (#7078) Gilad S 2024-05-08 22:08:10 +03:00
  • 212982e41d main : add --conversation / -cnv flag (#7108) Dawid Potocki 2024-05-09 02:32:32 +12:00
  • 83330d8cd6 main : add --conversation / -cnv flag (#7108) Dawid Potocki 2024-05-09 02:32:32 +12:00
  • 99dda84329 sgemm : AVX Q4_0 and Q8_0 (#6891) Eve 2024-05-08 14:29:23 +00:00
  • 465263d0cf sgemm : AVX Q4_0 and Q8_0 (#6891) Eve 2024-05-08 14:29:23 +00:00
  • 5274298a1f server : add_special option for tokenize endpoint (#7059) Johan 2024-05-08 14:27:58 +02:00
  • 911b3900dd server : add_special option for tokenize endpoint (#7059) Johan 2024-05-08 14:27:58 +02:00
  • 6d99b1f0e8 convert.py : --vocab-only generates false but valid params (#7027) 20kdc 2024-05-08 13:22:32 +01:00
  • ad211edef5 convert.py : --vocab-only generates false but valid params (#7027) 20kdc 2024-05-08 13:22:32 +01:00
  • 269bdbb907 llama : add BPE pre-tokenization for Qwen2 (#7114) Ren Xuancheng 2024-05-08 20:06:43 +08:00
  • 229ffff872 llama : add BPE pre-tokenization for Qwen2 (#7114) Ren Xuancheng 2024-05-08 20:06:43 +08:00
  • 777e128db5 clean up json_value & server_log (#7142) Xuan Son Nguyen 2024-05-08 13:24:14 +02:00
  • 1fd9c1741d clean up json_value & server_log (#7142) Xuan Son Nguyen 2024-05-08 13:24:14 +02:00
  • 6604fe6bb6 convert : add BPE pre-tokenization for DBRX (#7132) DAN™ 2024-05-08 06:43:23 -04:00
  • 4cd621c26d convert : add BPE pre-tokenization for DBRX (#7132) DAN™ 2024-05-08 06:43:23 -04:00
  • 65f2dd3a18 py : also print the normalizers Georgi Gerganov 2024-05-08 12:47:07 +03:00
  • 7e0b6a7b3b py : also print the normalizers Georgi Gerganov 2024-05-08 12:47:07 +03:00
  • b92591544f compare-llama-bench.py: add missing basicConfig (#7138) Brian 2024-05-08 18:54:39 +10:00
  • acdce3cdef compare-llama-bench.py: add missing basicConfig (#7138) Brian 2024-05-08 18:54:39 +10:00
  • 8474c73a90 ggml : introduce bfloat16 support (#6412) Justine Tunney 2024-05-08 02:30:09 -04:00
  • 3855416027 ggml : introduce bfloat16 support (#6412) Justine Tunney 2024-05-08 02:30:09 -04:00
  • 9e25235b25 metal : fix unused warning Georgi Gerganov 2024-05-08 09:14:50 +03:00
  • c0e6fbf8c3 metal : fix unused warning Georgi Gerganov 2024-05-08 09:14:50 +03:00
  • 22d71e8f84 Further tidy on Android instructions README.md (#7077) Jeximo 2024-05-07 21:26:43 -03:00
  • c780e75305 Further tidy on Android instructions README.md (#7077) Jeximo 2024-05-07 21:26:43 -03:00
  • 13b418643f Fixed save_imatrix to match old behaviour for MoE (#7099) jukofyork 2024-05-08 01:24:16 +01:00
  • 48b2f9c1fc Fixed save_imatrix to match old behaviour for MoE (#7099) jukofyork 2024-05-08 01:24:16 +01:00
  • e56a09c3dd server: fix incorrectly reported token probabilities (#7125) Johannes Gäßler 2024-05-07 23:07:58 +02:00
  • af0a5b6163 server: fix incorrectly reported token probabilities (#7125) Johannes Gäßler 2024-05-07 23:07:58 +02:00
  • 9bf2c358fe Fix OLMo HF to GGUF conversion (#6910) nopperl 2024-05-07 19:39:43 +00:00
  • b6aa670203 Fix OLMo HF to GGUF conversion (#6910) nopperl 2024-05-07 19:39:43 +00:00
  • b05d2abcaf server : update readme with undocumented options (#7013) Kyle Mistele 2024-05-07 13:44:29 -05:00
  • 260b7c6529 server : update readme with undocumented options (#7013) Kyle Mistele 2024-05-07 13:44:29 -05:00
  • 909d5c5eb3 readme : update hot topics Georgi Gerganov 2024-05-07 21:43:13 +03:00
  • 53d6c52e22 readme : update hot topics Georgi Gerganov 2024-05-07 21:43:13 +03:00
  • 8da74b0442 main : update log text (EOS to EOG) (#7104) RhinoDevel 2024-05-07 19:51:31 +02:00
  • 3af34c1d1b main : update log text (EOS to EOG) (#7104) RhinoDevel 2024-05-07 19:51:31 +02:00
  • 9478c760a8 docs: fix typos (#7124) omahs 2024-05-07 17:20:33 +02:00
  • 04976db7a8 docs: fix typos (#7124) omahs 2024-05-07 17:20:33 +02:00
  • f12d817695 ci : add GG_BUILD_EXTRA_TESTS_0 env (#7098) Georgi Gerganov 2024-05-07 11:08:49 +03:00
  • 947d3ad27d ci : add GG_BUILD_EXTRA_TESTS_0 env (#7098) Georgi Gerganov 2024-05-07 11:08:49 +03:00
  • 2903554f11 Add an option to build without CUDA VMM (#7067) William Tambellini 2024-05-06 11:12:14 -07:00
  • 858f6b73f6 Add an option to build without CUDA VMM (#7067) William Tambellini 2024-05-06 11:12:14 -07:00
  • 044f7e12a0 flake.lock: Update (#7079) Georgi Gerganov 2024-05-06 18:36:06 +03:00
  • b3a995b416 flake.lock: Update (#7079) Georgi Gerganov 2024-05-06 18:36:06 +03:00
  • a50a6f0d38 minor : fix trailing whitespace Georgi Gerganov 2024-05-06 09:31:30 +03:00
  • bcdee0daa7 minor : fix trailing whitespace Georgi Gerganov 2024-05-06 09:31:30 +03:00
  • 2e7eab33b5 Adding support for the --numa argument for llama-bench. (#7080) kunnis 2024-05-05 07:17:47 -05:00
  • 628b299106 Adding support for the --numa argument for llama-bench. (#7080) kunnis 2024-05-05 07:17:47 -05:00
  • 484922ff64 Disable benchmark on forked repo (#7034) Sigbjørn Skjæret 2024-05-05 13:38:55 +02:00
  • 8f8acc8683 Disable benchmark on forked repo (#7034) Sigbjørn Skjæret 2024-05-05 13:38:55 +02:00
  • f075684c64 readme : add note that LLaMA 3 is not supported with convert.py (#7065) Lyle Dean 2024-05-05 06:21:46 +01:00
  • ca36326020 readme : add note that LLaMA 3 is not supported with convert.py (#7065) Lyle Dean 2024-05-05 06:21:46 +01:00
  • 591a32f4f1 command-r : add BPE pre-tokenization (#7063) DAN™ 2024-05-05 01:19:30 -04:00
  • 889bdd7686 command-r : add BPE pre-tokenization (#7063) DAN™ 2024-05-05 01:19:30 -04:00
  • a921bd0c81 py : logging and flake8 suppression refactoring (#7081) Brian 2024-05-05 15:07:48 +10:00
  • 6fbd432211 py : logging and flake8 suppression refactoring (#7081) Brian 2024-05-05 15:07:48 +10:00
  • a93233ac8c gguf-split: add --no-tensor-first-split (#7072) Xuan Son Nguyen 2024-05-04 18:56:22 +02:00
  • 842500144e gguf-split: add --no-tensor-first-split (#7072) Xuan Son Nguyen 2024-05-04 18:56:22 +02:00
  • 6b77c2c457 Tidy Android Instructions README.md (#7016) Jeximo 2024-05-04 13:10:15 -03:00
  • cf768b7e71 Tidy Android Instructions README.md (#7016) Jeximo 2024-05-04 13:10:15 -03:00
  • 32892232a7 Fix Linux /sys cpu path to guess number of cores (#7064) viric 2024-05-04 15:26:53 +02:00
  • fcd84a0f5a Fix Linux /sys cpu path to guess number of cores (#7064) viric 2024-05-04 15:26:53 +02:00
  • 68c2749a8a If first token generated from the server is the stop word the server will crash (#7038) maor-ps 2024-05-04 12:06:40 +03:00
  • 03fb8a002d If first token generated from the server is the stop word the server will crash (#7038) maor-ps 2024-05-04 12:06:40 +03:00
  • b518940ede tests : add test-tokenizer-0.sh + fix some tokenizers (#7036) Georgi Gerganov 2024-05-04 08:32:32 +03:00
  • 92139b90af tests : add test-tokenizer-0.sh + fix some tokenizers (#7036) Georgi Gerganov 2024-05-04 08:32:32 +03:00
  • 7bd1c13a56 convert.py : add python logging instead of print() (#6511) Brian 2024-05-04 05:36:41 +10:00
  • a2ac89d6ef convert.py : add python logging instead of print() (#6511) Brian 2024-05-04 05:36:41 +10:00
  • 44376cfc88 llama : rename ctx to user_data in progress_callback (#7045) Daniel Bevenius 2024-05-03 15:24:30 +02:00
  • 433def286e llama : rename ctx to user_data in progress_callback (#7045) Daniel Bevenius 2024-05-03 15:24:30 +02:00
  • abde0cec51 Remove .attention from skipped tensors to match more accurately (#7051) Bartowski 2024-05-02 19:49:09 -04:00
  • 60325fa56f Remove .attention from skipped tensors to match more accurately (#7051) Bartowski 2024-05-02 19:49:09 -04:00
  • 7484433b02 chore: fix typo in llama.cpp (#7032) alwqx 2024-05-02 23:56:41 +08:00
  • 6ecf3189e0 chore: fix typo in llama.cpp (#7032) alwqx 2024-05-02 23:56:41 +08:00
  • 5bc5f1f361 Update LOG_IMPL and LOG_TEE_IMPL (#7029) Andrew Downing 2024-05-01 17:31:30 -04:00
  • b0d943de17 Update LOG_IMPL and LOG_TEE_IMPL (#7029) Andrew Downing 2024-05-01 17:31:30 -04:00
  • 95345759c3 main : fix off by one error for context shift (#6921) l3utterfly 2024-05-02 04:27:41 +09:00
  • 8d608a81b7 main : fix off by one error for context shift (#6921) l3utterfly 2024-05-02 04:27:41 +09:00
  • a350b6a103 Server: add tests for batch size, different seeds (#6950) Johannes Gäßler 2024-05-01 17:52:55 +02:00
  • 3ea0d36000 Server: add tests for batch size, different seeds (#6950) Johannes Gäßler 2024-05-01 17:52:55 +02:00
  • 2dd44593ef CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019) Johannes Gäßler 2024-05-01 14:46:37 +02:00
  • 1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019) Johannes Gäßler 2024-05-01 14:46:37 +02:00
  • 82e7f68958 ci : exempt confirmed bugs from being tagged as stale (#7014) slaren 2024-05-01 07:13:59 +02:00
  • c4ec9c0d3d ci : exempt confirmed bugs from being tagged as stale (#7014) slaren 2024-05-01 07:13:59 +02:00
  • 5ab303493c perplexity: more statistics, added documentation (#6936) Johannes Gäßler 2024-04-30 23:36:27 +02:00
  • a8f9b07631 perplexity: more statistics, added documentation (#6936) Johannes Gäßler 2024-04-30 23:36:27 +02:00