Commit Graph

  • cf794133de xcf : use check for visionos build version (#3021) Daniel Bevenius 2025-04-09 16:34:58 +02:00
  • ef6cf357e7 ruby : fix types of arguments for rb_get_kwargs in ruby_whisper_params.c (#3022) Olli 2025-04-09 13:49:25 +02:00
  • b1f5c11b32 ruby : Update uri.rb (#3016) Olli 2025-04-08 15:27:40 +02:00
  • ada745f4a5 models : fix dead link to models in readme (#3006) Greg Sadetsky 2025-04-06 01:29:41 -04:00
  • 01985c22c0 ruby : change homepage URI in Ruby gemspec (#3007) KITAITI Makoto 2025-04-05 13:55:09 +09:00
  • 448f3d3b93 tests : add script to benchmark whisper.cpp on LibriSpeech corpus (#2999) Fujimoto Seiji 2025-04-05 01:51:26 +09:00
  • e6234cd435 whisper : fix "bench-all outputs an invalid result on larger models" (#3002) Fujimoto Seiji 2025-04-05 00:36:19 +09:00
  • 2b6d0d2200 rename : ggerganov -> ggml-org (#3005) Georgi Gerganov 2025-04-04 16:11:52 +03:00
  • 0b17d4507e examples : update server.py to match github pages app [no ci] (#3004) Daniel Bevenius 2025-04-04 10:23:53 +02:00
  • 77e0c86ab6 whisper.wasm : fix unknown language issue (#3000) Daniel Bevenius 2025-04-03 19:50:47 +02:00
  • eac1bc9c47 examples : add new sources Georgi Gerganov 2025-04-02 15:24:02 +03:00
  • cbde66d913 sync : ggml Georgi Gerganov 2025-04-02 15:23:55 +03:00
  • 513ecf8dc0 cpu: move all the operators into a separate c++ file (except mul_mat) (ggml/1167) cmdr2 2025-04-02 17:46:16 +05:30
  • cce5daf17b docs : add xcframework section to README.md [no ci] (#2997) Daniel Bevenius 2025-04-03 09:06:53 +02:00
  • 2c502b3c00 readme : update roadmap link Georgi Gerganov 2025-04-02 17:38:35 +03:00
  • 51c6961c7b release : v1.7.5 v1.7.5 Georgi Gerganov 2025-04-02 16:31:22 +03:00
  • 503a786c9a bench : update numbers [no ci] (#2993) Georgi Gerganov 2025-04-02 16:27:36 +03:00
  • e400aeb770 examples : add new sources sync-ggml-25-04-02-2 Georgi Gerganov 2025-04-02 15:24:02 +03:00
  • cb9a21b957 sync : ggml Georgi Gerganov 2025-04-02 15:23:55 +03:00
  • dacb7caed6 cpu: move all the operators into a separate c++ file (except mul_mat) (ggml/1167) cmdr2 2025-04-02 17:46:16 +05:30
  • ad4e350933 sync : ggml Georgi Gerganov 2025-04-02 15:13:40 +03:00
  • d7a9346ab1 get_rows and dup optimization (llama/12671) Chenguang Li 2025-04-02 15:22:13 +08:00
  • b63d23f728 opencl : fix memory allocation size (llama/12649) Junil Kim 2025-04-02 01:54:34 +09:00
  • f6ce10e4a1 metal : use F32 prec in FA kernels (llama/12688) Georgi Gerganov 2025-04-01 14:57:19 +03:00
  • 6cb2b86581 Fix clang warning in gguf_check_reserved_keys (llama/12686) R0CKSTAR 2025-04-01 19:12:53 +08:00
  • 801d6bd809 vulkan: fix build when glslc doesn't support coopmat (llama/12683) Wagner Bruna 2025-04-01 06:38:07 -03:00
  • ddf7e6a15d SYCL: Rename oneMKL to oneMath (llama/12192) Romain Biessy 2025-04-01 10:24:29 +02:00
  • 0d42097fd3 SYCL: switch to SYCL namespace (llama/12674) Akarshan Biswas 2025-04-01 13:41:39 +05:30
  • 842b9c984c ggml : faster ssm scan (llama/10558) a3sh 2025-04-01 00:05:13 +08:00
  • 0810f02547 Vulkan: Add DP4A MMQ and Q8_1 quantization shader (llama/12135) 0cc4m 2025-03-31 14:37:01 +02:00
  • 8c13c78f9d cmake : fix whitespace (llama/0) Georgi Gerganov 2025-03-31 15:05:30 +03:00
  • f31b404fcb tests : remove gh label test-whisper-cli-tiny-en (#2988) Daniel Bevenius 2025-04-02 10:50:31 +02:00
  • 854c0518bc examples : clarify Core ML encoder model usage [no ci] (#2987) Daniel Bevenius 2025-04-02 08:32:14 +02:00
  • c8e3968edd ci : remove intermediate build on push to master (#2986) Daniel Bevenius 2025-04-02 08:29:28 +02:00
  • b358de2458 whisper.objc : fix typo in README.md [no ci] (#2985) Daniel Bevenius 2025-04-02 08:26:57 +02:00
  • 11688b262f coreml: fix Whisper to CoreML conversion by disabling SDPA [no ci] (#2979) Daniel Bevenius 2025-04-01 18:01:23 +02:00
  • 04b9508fb3 ci : add coreml job that converts base.en to coreml [no ci] (#2981) Daniel Bevenius 2025-04-01 17:04:32 +02:00
  • 4200430e75 tests : re-enable tests [no ci] (#2977) Daniel Bevenius 2025-03-31 17:04:37 +02:00
  • e153b8eaa2 android.java : re-add ggml source updates (#2975) b2365 Daniel Bevenius 2025-03-31 16:14:33 +02:00
  • 83af237f0b ci : re-enable freeBDS-latest job (#2973) b2364 Daniel Bevenius 2025-03-31 15:24:08 +02:00
  • 7a2e39750a ci : re-enable android_java job (#2958) Daniel Bevenius 2025-03-31 15:14:24 +02:00
  • 0a40ae9728 android : add new ggml source files b2362 Georgi Gerganov 2025-03-31 14:38:43 +03:00
  • 32cfdcbf42 ruby : add new ggml sources Georgi Gerganov 2025-03-31 14:19:25 +03:00
  • cfa42aca09 sync : ggml Georgi Gerganov 2025-03-31 14:13:54 +03:00
  • 2e2f0f954b SYCL: Remove misleading ggml_sycl_op_flatten function (llama/12387) Akarshan Biswas 2025-03-31 14:55:24 +05:30
  • 93631b2be6 metal : use constexpr in FA kernels + fix typedef (llama/12659) Georgi Gerganov 2025-03-30 22:04:04 +03:00
  • f9015b585b musa: fix all warnings, re-enable -DLLAMA_FATAL_WARNINGS=ON in ci and update doc (llama/12611) R0CKSTAR 2025-03-30 16:59:38 +08:00
  • 1880ffd7ff cmake : fix ccache conflict (llama/12522) Jay 2025-03-29 18:04:58 +08:00
  • 9173932c78 cpu : rm unused variable (ggml/1166) Xuan-Son Nguyen 2025-03-29 11:59:56 +01:00
  • 94c3f3877f cpu: de-duplicate some of the operators and refactor (ggml/1144) cmdr2 2025-03-29 11:37:13 +05:30
  • 00086469fb cmake: improve Vulkan cooperative matrix support checks (#2966) b2353 Sandro Hanea 2025-03-31 12:44:36 +02:00
  • 2d8e40e2a0 examples : update README links to point to pages deployment (#2971) b2352 Daniel Bevenius 2025-03-31 12:32:27 +02:00
  • e17af6524f ci : add github pages workflow for wasm examples (#2969) b2351 Daniel Bevenius 2025-03-31 11:34:40 +02:00
  • 88d13a17a7 feat: add health check endpoint to server (#2968) b2350 Sacha Arbonel 2025-03-31 10:03:41 +02:00
  • f92bd59951 whisper : remove unnecessary GGML_UNUSED macro (#2960) b2349 Daniel Bevenius 2025-03-30 05:56:10 +02:00
  • 6e7629b146 sync : ggml b2348 Georgi Gerganov 2025-03-28 20:58:21 +02:00
  • 27533e7f63 metal : improve FA + improve MoE (llama/12612) Georgi Gerganov 2025-03-28 20:21:59 +02:00
  • 1b81415963 vulkan: fix coopmat shader generation when cross-compiling (llama/12272) Icenowy Zheng 2025-03-29 01:51:06 +08:00
  • 0001ec075f llamafile : ppc64le GEMV forwarding for FP32. (llama/12594) amritahs-ibm 2025-03-28 13:13:22 +05:30
  • 5bad2e5099 rpc : send hash when tensor data is above some fixed threshold (llama/12496) Radoslav Gerganov 2025-03-28 08:18:04 +02:00
  • 6fc0ae2f5a opencl: add multi and vision rope, gelu_quick and im2col (llama/12600) lhez 2025-03-27 08:08:08 -07:00
  • de6b38c6d9 bindings.go : add DetectedLanguage to go bindings (#2947) b2342 Amanda Der Bedrosian 2025-03-28 04:26:22 -07:00
  • 46d6e0abc1 ruby : fix test failures in test_whisper (#2955) b2341 Daniel Bevenius 2025-03-28 09:29:56 +01:00
  • 1279f0d0bc examples : support progress_callback API for addon.node (#2941) b2340 Lin Xiaodong 2025-03-28 13:34:26 +08:00
  • f28bf5d186 xcf : fix visionOS build b2339 Georgi Gerganov 2025-03-27 10:30:09 +02:00
  • 1fbdfb1d36 files : remove old wkv6 (#0) Georgi Gerganov 2025-03-27 10:15:02 +02:00
  • ee5581633b sync : ggml Georgi Gerganov 2025-03-27 10:13:47 +02:00
  • 8ca67df291 ggml : sync/merge cmake,riscv,powerpc, add common.cmake (ggml/0) Georgi Gerganov 2025-03-27 09:12:54 +02:00
  • fc6d343e76 llamafile : ppc64le MMA implementation for Q4_0. (llama/12489) amritahs-ibm 2025-03-27 12:21:47 +05:30
  • 3199356d3a SYCL: implement memset ggml backend buffer interface (llama/12580) Akarshan Biswas 2025-03-27 07:16:00 +05:30
  • e0c43b0bbf HIP: Add support for RDNA4 targets (llama/12372) Slobodan Josic 2025-03-26 23:46:30 +01:00
  • f4f619ea8e metal : refactor mat-vec code (llama/12569) Georgi Gerganov 2025-03-26 21:38:38 +02:00
  • 3c4d363872 ggml : fix MUL_MAT_ID repack with Q8_K (llama/12544) Georgi Gerganov 2025-03-26 13:02:00 +02:00
  • 15aa189329 ggml-cpu : update KleidiAI to v1.5.0 (llama/12568) Dan Johansson 2025-03-25 12:10:18 +01:00
  • c53d5c9e85 SYCL: disable Q4_0 reorder optimization (llama/12560) Akarshan Biswas 2025-03-25 16:10:18 +05:30
  • ba6f584f30 opencl: simplify kernel embedding logic in cmakefile (llama/12503) lhez 2025-03-24 09:20:47 -07:00
  • a219941812 CUDA: Fix clang warnings (llama/12540) R0CKSTAR 2025-03-24 18:28:34 +08:00
  • a2cc8c2666 vulkan: fix mul_mat_vec failure in backend tests (llama/12529) Jeff Bolz 2025-03-24 01:56:17 -05:00
  • 388ed98220 ggml : fix quantized cpy op (llama/12310) Georgi Gerganov 2025-03-22 16:23:26 +02:00
  • d487a28ae1 musa: refine compute capability (llama/12493) R0CKSTAR 2025-03-22 17:11:37 +08:00
  • cbb88c4050 vulkan: Optimize mul_mat_vec p021 and nc shaders (llama/12505) Jeff Bolz 2025-03-22 03:40:11 -05:00
  • 13455c0b5f Vulkan: RTE rounding for cpy to quant (llama/12480) stduhpf 2025-03-21 20:34:50 +01:00
  • 2f77a9e9bd vulkan: workaround for AMD Windows driver 16 bit unpack8 bug (llama/12472) Eve 2025-03-21 19:27:47 +00:00
  • fa2b5249ff Fix build on Windows when ccache enabled (ggml/9954) (llama/9976) 蕭澧邦 2025-03-21 14:58:47 +08:00
  • 5b854ebba5 sycl: cleanup oneDNN related code (llama/12097) Svetlozar Georgiev 2025-03-21 02:15:56 +00:00
  • 8058f19d0b ggml : block interleaving support for Q4_K quantization for x86 AVX2 architecture (llama/12332) Srihari-mcw 2025-03-20 17:05:34 +05:30
  • ae6a9bb9a5 CUDA: Improve flash decoding kernel GPU occupancy for BS=1 case (llama/12183) Gaurav Garg 2025-03-20 01:22:06 +05:30
  • 24faba9e9b vulkan: optimize iq1 coopmat2 dequant functions (llama/12427) Jeff Bolz 2025-03-19 13:56:23 -05:00
  • c722ff84d3 Fix visionOS build and add CI (llama/12415) Guus Waals 2025-03-19 10:15:23 +00:00
  • 102af79f63 vulkan: Submit once enough matmul work has been recorded (llama/12406) Jeff Bolz 2025-03-19 02:26:26 -05:00
  • 03c364557d opencl: improve profiling (llama/12442) lhez 2025-03-18 12:54:55 -07:00
  • 31b62276cf musa: override warp_size of musa device to 32 (llama/12445) R0CKSTAR 2025-03-19 02:28:26 +08:00
  • 97b5a3055d SYCL: using graphs is configurable by environment variable and compile option (llama/12371) Łukasz Ślusarczyk 2025-03-18 11:16:31 +01:00
  • 9993c3f703 ggml : add SVE support for q6_K_q8_K (llama/12361) fj-y-saito 2025-03-18 17:14:39 +09:00
  • fa72479cfb Vulkan: Default to 1GB allocations instead of 4GB to avoid fragmentation and driver issues (llama/12434) 0cc4m 2025-03-18 07:21:40 +01:00
  • 6c15539c54 fixed compilation warnings in ggml-sycl (llama/12424) Łukasz Ślusarczyk 2025-03-18 01:51:25 +01:00
  • 52c4c03b0a llama: Add support for RWKV v7 architecture (llama/12412) Molly Sophia 2025-03-18 07:27:50 +08:00
  • cfc2560e41 cuda : enable CUDA Graph on CUDA Toolkit < 12.x (llama/12394) Gaurav Garg 2025-03-17 23:55:13 +05:30
  • db6e8056b5 ggml-vulkan: remove unused find_program(glslc) (llama/12416) Guus Waals 2025-03-18 00:35:43 +08:00
  • b3f3779c1b vulkan: Add N/2 and N/4 optimized paths in coopmat2 shader (llama/12312) Jeff Bolz 2025-03-17 09:26:18 -05:00