Commit Graph

  • ccf022f970 bindings/go : add linker flags to make metal work (#1944) Josh Bleecher Snyder 2024-03-09 08:50:44 -08:00
  • 2852e1af55 whisper : make beam candidate sort more stable (#1943) Josh Bleecher Snyder 2024-03-09 08:50:03 -08:00
  • ce945b50c3 ggml : try fix 32-bit arm compat (#1938) Georgi Gerganov 2024-03-08 23:45:07 +02:00
  • 2f5a5a66dd talk-llama : use llama_decode instead of llama_eval Georgi Gerganov 2024-03-08 12:04:43 +02:00
  • 8e409d1113 talk-llama : sync llama.cpp Georgi Gerganov 2024-03-08 11:55:50 +02:00
  • 05d1b61af4 talk-llama : sync llama.cpp Georgi Gerganov 2024-03-08 11:52:47 +02:00
  • 647cae178a sync : ggml Georgi Gerganov 2024-03-08 11:39:34 +02:00
  • bae7c23fbf Revert "[SYCL] fix error when set main gpu to non-zero (llama/5901)" (llama/5918) Neo Zhang Jianyu 2024-03-07 19:14:49 +08:00
  • 18ea187d42 fix error when set main gpu to non-zero (llama/5901) Neo Zhang Jianyu 2024-03-07 16:34:31 +08:00
  • 1daeffca54 ggml : use SYS_get_cpu if SYS_getcpu is not defined (llama/5906) Jared Van Bortel 2024-03-06 15:42:23 -05:00
  • 2f6f1d4465 ggml : use uint8x16_t return type for ggml_vqtbl1q_u8 (llama/5894) bobqianic 2024-03-06 07:35:07 +00:00
  • 7ff1894c34 add wait() to make code stable (llama/5895) Neo Zhang Jianyu 2024-03-06 12:08:32 +08:00
  • 8edfc54c2b quants : use MM256_SET_M128I consistently to fix gcc 7 build (llama/5889) Jared Van Bortel 2024-03-05 11:56:37 -05:00
  • 9c399689ec Vulkan Improvements (llama/5835) 0cc4m 2024-03-05 13:33:42 +01:00
  • 9d9a405cfd fix mul_mat fault in CI/unit-test (llama/5862) Neo Zhang Jianyu 2024-03-05 16:08:35 +08:00
  • edd8b38a75 ggml : fix unknown status (llama/0) Georgi Gerganov 2024-03-04 20:53:27 +02:00
  • ed76818700 whisper : fix compute helper return (ggml/750) Georgi Gerganov 2024-03-05 16:05:23 +02:00
  • 9a0b59d990 ggml : introduce ggml_status (ggml/750) Michael Podvitskiy 2024-03-04 10:05:42 +01:00
  • 93a84a143b cuda : fix data race in soft max (llama/5853) slaren 2024-03-03 14:26:18 +01:00
  • bd26876267 ggml : fix IQ3_S AVX implementation (llama/5834) Georgi Gerganov 2024-03-02 20:00:49 +02:00
  • 21d295180d ggml : IQ3_S improvements (llama/5829) Kawrakow 2024-03-02 17:00:51 +02:00
  • c3bfc9bfda Support multiple GPUs (split mode) on SYCL backend (llama/5806) Neo Zhang Jianyu 2024-03-02 19:49:30 +08:00
  • 422a6b16fc ggml-vulkan: fix VULKAN_CHECK_RESULTS flag, which was previously broken (llama/5813) ddpasa 2024-03-01 18:00:00 +01:00
  • 11dd0d4482 Use batched mul_mat pathway (llama/5591) AidanBeltonS 2024-03-01 07:36:47 +00:00
  • 26dd2f06ac make portability_enumeration_ext apple only (llama/5757) Eve 2024-02-28 19:33:37 +00:00
  • 8cee7c08b6 add some new ops, fix some operators and add batch operations to certain operators. (ggml/747) leejet 2024-03-03 20:23:52 +08:00
  • 2e2626b167 examples : Auto lowercase language parameter in main.cpp (#1928) F1L1P 2024-03-06 23:25:10 +01:00
  • c0c0ae2dea examples : fix typo in bench.cpp (#1933) zhouwg 2024-03-07 06:21:44 +08:00
  • 897412b5b6 whisper : fix typo (#1925) zhouwg 2024-03-05 23:06:31 +08:00
  • f22d27a385 whisper.android.java : fix returns in JNI (#1929) zhouwg 2024-03-05 21:59:26 +08:00
  • ccd7c1d2da cmake : add library versioning (#1352) kennethge 2024-03-04 14:17:48 -05:00
  • c713eb5e2a readme : recommend MacOS Sonoma for Core ML (#1917) Gavin Cai 2024-03-04 11:16:13 -08:00
  • 25d313b38b talk-llama : sync llama.cpp Georgi Gerganov 2024-02-28 13:04:05 +02:00
  • 3168dbf23b sync : ggml Georgi Gerganov 2024-02-28 13:01:33 +02:00
  • 1711bb3881 sync : llama.cpp (ggml/0) Georgi Gerganov 2024-02-28 12:59:11 +02:00
  • 2533305596 ggml : make i-quants work with super-blocks of 64 (CPU,Metal) (llama/5760) Kawrakow 2024-02-28 10:37:02 +02:00
  • 0eca512ac8 Attempt to fix android build (llama/5752) Kawrakow 2024-02-27 19:16:49 +02:00
  • 013e394a4b IQ4_XS: a 4.25 bpw quantization (llama/5747) Kawrakow 2024-02-27 16:34:24 +02:00
  • d83f371b5f cuda : replace remaining shfl_xor with calls to warp_reduce functions (llama/5744) Engininja2 2024-02-27 07:22:45 -06:00
  • 1c71816eab ggml-quants : fix avx2 iq1_s vec_dot when compiled with gcc (llama/5742) Engininja2 2024-02-27 06:50:18 -06:00
  • 7b1d8ea7e0 Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (llama/5721) Kawrakow 2024-02-26 18:28:38 +02:00
  • b1f7223a0a CUDA: fix DEBUG_CUDA_MALLOC (llama/5729) Johannes Gäßler 2024-02-26 15:36:38 +01:00
  • 8408a4be8e Add support for soft_max ALiBi (llama/5639) AidanBeltonS 2024-02-26 14:02:11 +00:00
  • 72849c24ba ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (llama/5711) Radosław Gryta 2024-02-25 19:43:00 +01:00
  • c19c28be71 add google magika inference example (ggml/748) slaren 2024-02-25 20:41:35 +01:00
  • 0d8fd8483a stream.wasm : fix invalid memory access when no segments (#1902) Andrew S 2024-02-26 02:12:35 -06:00
  • 3170841ed9 talk-llama : sync llama.cpp Georgi Gerganov 2024-02-25 20:00:10 +02:00
  • 7a6e385c1b sync : ggml Georgi Gerganov 2024-02-25 19:59:34 +02:00
  • 578e47e70c sync : llama.cpp (ggml/0) Georgi Gerganov 2024-02-25 19:58:06 +02:00
  • fac5b43830 code : normalize enum names (llama/5697) Georgi Gerganov 2024-02-25 12:09:09 +02:00
  • 9e7c5212a1 IQ3_S: a much better alternative to Q3_K (llama/5676) Kawrakow 2024-02-24 16:23:52 +02:00
  • 1cb64f7368 Introduce backend GUIDs (ggml/743) UEXTM.com 2024-02-24 11:27:36 -05:00
  • f18738f247 talk, talk-llama : pass text_to_speak as a file (#1865) Tamotsu Takahashi 2024-02-24 16:24:47 +09:00
  • a0ddd8392c whisper : add SYCL support (#1863) Abhilash Majumder 2024-02-23 12:52:24 +05:30
  • a2506909b1 talk-llama : sync llama.cpp Georgi Gerganov 2024-02-22 23:30:53 +02:00
  • 7b1ff212d9 sync : ggml Georgi Gerganov 2024-02-22 23:25:38 +02:00
  • e5d06cfc0f ggml : always define ggml_fp16_t as uint16_t (llama/5666) Georgi Gerganov 2024-02-22 23:21:39 +02:00
  • 31891db2e3 ci : fix whitespace Georgi Gerganov 2024-02-22 20:20:34 +02:00
  • 5fdb27ff80 ggml : 32-bit arm compat (#1891) Georgi Gerganov 2024-02-22 18:31:40 +02:00
  • 6b16927d18 sync : ggml Georgi Gerganov 2024-02-22 15:15:38 +02:00
  • ce411498f6 sync : llama.cpp (ggml/0) Georgi Gerganov 2024-02-21 16:19:39 +02:00
  • 208de95ac7 conext add name (llama/5624) Meng, Hengyu 2024-02-21 17:52:06 +08:00
  • c2ce39c795 Update ggml_sycl_op_mul_mat_vec_q (llama/5502) AidanBeltonS 2024-02-20 07:01:25 +00:00
  • 8daa534818 Refactor validation and enumeration platform checks into functions to clean up ggml_vk_instance_init() 0cc4m 2024-02-14 20:57:17 +01:00
  • 9fca69b410 Add check for VK_KHR_portability_enumeration for MoltenVK support 0cc4m 2024-02-10 22:14:52 +01:00
  • b26c645420 Add preprocessor checks for Apple devices. Mathijs de Bruin 2024-02-06 14:39:22 +00:00
  • 1879ec556e Resolve ErrorIncompatibleDriver with Vulkan on MacOS. Mathijs de Bruin 2024-02-03 18:00:11 +00:00
  • c6e53cfc46 Allow for Vulkan build with Accelerate. Mathijs de Bruin 2024-02-03 17:56:46 +00:00
  • b19f2fb815 cuda : ignore peer access already enabled errors (llama/5597) slaren 2024-02-19 23:40:26 +01:00
  • a6b0950916 ggml : compute forward no longer pass src tensors (ggml/729) Siddharth Ramakrishnan 2024-02-21 04:34:53 -08:00
  • d352dbd163 ggml : fix conv_2d batch mode (ggml/737) bssrdf 2024-02-20 14:17:09 -05:00
  • eb23f4ef16 openvino : fix convert-whisper-to-openvino.py (#1890) st-gr 2024-02-22 05:11:35 -08:00
  • c56344b509 main : fix file existence check in main.cpp (#1889) Davidson Francis 2024-02-22 10:01:08 -03:00
  • 59119f4f20 talk-llama : sync llama.cpp Georgi Gerganov 2024-02-20 12:09:57 +02:00
  • 276615d708 make : fix CUBLAS link with WSL (#1878) LBlue 2024-02-20 18:05:38 +08:00
  • b602819b6e sync : ggml Georgi Gerganov 2024-02-19 15:54:25 +02:00
  • c2c606f05b ggml : resolve merge conflicts (ggml/0) Georgi Gerganov 2024-02-19 15:33:51 +02:00
  • 83afebe872 common : add IQ1_S (ggml/0) Georgi Gerganov 2024-02-19 15:27:37 +02:00
  • a4d8f9d559 ci : enable -Werror for CUDA builds (llama/5579) Georgi Gerganov 2024-02-19 14:45:41 +02:00
  • 5ec1e0edfa cuda, metal : fix nans in soft_max (llama/5574) slaren 2024-02-19 09:04:45 +01:00
  • 30a11b1ab8 ggml : android and old glibc NUMA incompatibility bugfixes (llama/5557) bmwl 2024-02-18 23:38:32 -08:00
  • f04e6b87d7 ggml : restore vec dot stride arg names (llama/5453) Georgi Gerganov 2024-02-18 22:58:57 +02:00
  • 0c33928b55 ci : fix wikitext url + compile warnings (llama/5569) Georgi Gerganov 2024-02-18 22:39:30 +02:00
  • 0775374750 metal : fix unused warnings (llama/0) Georgi Gerganov 2024-02-18 21:39:58 +02:00
  • 7d90bb035b ggml, common, examples, tests : fixed type arguments in printf (llama/5528) Herman Semenov 2024-02-18 16:20:12 +00:00
  • 2c1ad21ba8 1.5 bit quantization (llama/5453) Kawrakow 2024-02-18 18:16:55 +02:00
  • eca5ff9868 ggml : add ALiBi support for ggml_soft_max_ext (llama/5488) Georgi Gerganov 2024-02-19 15:18:09 +02:00
  • 1b25d2fa0a ci : add an option to fail on compile warning (llama/3952) Ananta Bastola 2024-02-17 16:03:14 -05:00
  • 74a6acc999 cmake : fix VULKAN and ROCm builds (llama/5525) Georgi Gerganov 2024-02-16 19:05:56 +02:00
  • a4ed8a0821 ggml : add numa options (llama/5377) bmwl 2024-02-16 01:31:07 -08:00
  • 9f675e021c cuda : print message when initialization fails (llama/5512) slaren 2024-02-15 16:49:01 +01:00
  • a38efcb9fd vulkan: Find optimal memory type but with fallback (llama/5381) Neuman Vong 2024-02-15 17:11:15 +11:00
  • 31591649a0 Early return for zero size calls to get_tensor. (llama/5482) AT 2024-02-13 15:44:25 -06:00
  • 4f5c46a84f ggml-quants : fix compiler warnings (shadow variable) (llama/5472) Kawrakow 2024-02-13 09:07:57 +02:00
  • 462ffc58db ggml-sycl: Replace 3d ops with macro (llama/5458) Abhilash Majumder 2024-02-12 20:22:05 +05:30
  • 65faae0b6a build : update CBLAS flags + fix unused var warning (#0) Georgi Gerganov 2024-02-19 14:44:46 +02:00
  • dda4b0ed06 main : check if input files exist before proceeding (#1872) Davidson Francis 2024-02-19 05:51:26 -03:00
  • 07d04280be examples : clean up common code (#1871) Felix 2024-02-19 09:50:15 +01:00
  • 917c56ded4 models : fix openvino setup info (#1874) Jumper775 2024-02-18 21:19:47 -05:00
  • 3d42463845 models : add update py requirements Georgi Gerganov 2024-02-13 11:51:32 +02:00