Commit Graph

  • d91fea509b
    Merge 6c05cf7b0d into 31aea563a8 Bjarke Viksøe 2024-11-07 09:22:56 +0200
  • c17525682f
    Merge fbb8bc6c2f into 31aea563a8 Shi Liang 2024-11-06 16:07:10 -0600
  • 31aea563a8
    whisper : fix extra memory usage (#2534) master Vin Misra 2024-11-06 13:02:11 -0800
  • 82b3a12b6b Merge branch 'master' of https://github.com/vinmisra/whisper.cpp Vinith Misra 2024-11-06 05:48:10 -0800
  • 47b43994f9 Merge branch 'master' of https://github.com/vinmisra/whisper.cpp Vinith Misra 2024-11-06 05:46:06 -0800
  • 88e52703fc Merge branch 'master' of https://github.com/vinmisra/whisper.cpp Vinith Misra 2024-11-06 05:46:06 -0800
  • 3469ddebff passing samples_padded by ref to the threads. Vinith Misra 2024-11-06 05:04:38 -0800
  • 4a27fb417a passing samples_padded by ref to the threads. Vinith Misra 2024-11-06 05:04:38 -0800
  • d4940e6da7
    Merge 2651c3e2d4 into 0377596b77 shivghai 2024-11-06 04:55:17 -0800
  • a6ec8f575e
    Merge dac938391d into 0377596b77 Greener-Dalii 2024-11-05 11:23:29 -0500
  • eb64ee461c
    Merge 36dcb97180 into 0377596b77 mytang0 2024-11-04 00:30:50 +0100
  • ed9ebccea6
    Merge 69b3136171 into 0377596b77 Dave Lewis 2024-11-03 00:23:12 +0900
  • 6bf2dcc21d
    Merge 2963de6a20 into 0377596b77 shanelenagh 2024-11-02 21:02:44 +0800
  • aa4e3e44b4
    Merge 613f938ecf into 0377596b77 thewh1teagle 2024-11-01 20:15:29 +0200
  • ac33babb8b
    Merge 8d60666cbc into 0377596b77 Amanda Der Bedrosian 2024-11-01 17:02:37 +0000
  • fce03422a4 handle graceful shutdown + better logs Sacha Arbonel 2024-11-01 11:16:01 +0100
  • 8179d4e0d8 wip Sacha Arbonel 2024-11-01 10:49:14 +0100
  • 0377596b77 whisper : backend registry init before model load Georgi Gerganov 2024-10-31 22:53:46 +0200
  • c65d0fd3c8 talk-llama : sync llama.cpp Georgi Gerganov 2024-10-31 22:29:22 +0200
  • d9efb664ac sync : ggml Georgi Gerganov 2024-10-31 22:26:28 +0200
  • b5b4b0f5de ggml : add AMX backend (llama/8998) Ma Mingfei 2024-10-26 09:43:40 +0300
  • ab36d02560 metal : support permuted matrix multiplicaions (llama/10033) Georgi Gerganov 2024-10-25 22:26:15 +0300
  • 6e67749c00 CUDA: fix insufficient buffer clearing for MMQ (llama/10032) Johannes Gäßler 2024-10-24 14:40:23 +0200
  • ab0385f43b CUDA: fix MMQ for non-contiguous src0, add tests (llama/10021) Johannes Gäßler 2024-10-24 11:09:36 +0200
  • 10eb603a3c increase cuda_cpy block size (ggml/996) bssrdf 2024-10-23 14:34:00 -0400
  • a3231b2f2e metal : add POOL2D and fix IM2COL (llama/9943) Jun Hee Yoo 2024-10-23 19:33:45 +0900
  • 13db492f83 Adapt to dynamically loadable backends mechanism (llama/9970) leo-pony 2024-10-22 16:16:01 +0800
  • 741c138aa1 ggml : add asserts for type conversion in fattn kernels (llama/9971) Georgi Gerganov 2024-10-21 16:20:46 +0300
  • 25f9fee6fb rpc : pack only RPC structs (llama/9959) Radoslav Gerganov 2024-10-21 13:35:40 +0300
  • 7c1570bee6 fix mul_mat_vec_q and *_vec_q error (llama/9939) Neo Zhang Jianyu 2024-10-21 14:26:09 +0800
  • 4078e4c388 rpc : backend refactoring (llama/9912) Radoslav Gerganov 2024-10-18 14:33:58 +0300
  • a4a22daa8f Add SYCL Backend registry, device and Event Interfaces (llama/9705) Ouadie EL FAROUKI 2024-10-18 06:46:16 +0100
  • e1936eb2a5 add amx kernel for gemm (llama/8998) Ma Mingfei 2024-10-18 13:34:36 +0800
  • 28b044dad9 vulkan : add backend registry / device interfaces (llama/9721) Diego Devesa 2024-10-17 02:46:58 +0200
  • b8f11a0a17 fix: allocating CPU buffer with size 0 (llama/9917) Gilad S 2024-10-17 02:34:22 +0300
  • ff5a838099 fix: use vm_allocate to allocate CPU backend buffer on macOS (llama/9875) Gilad S 2024-10-17 01:36:51 +0300
  • 84713613be CUDA: fix 1D im2col, add tests (ggml/993) Johannes Gäßler 2024-10-18 09:24:44 +0200
  • ded89c9d08 Fix cann compilation error (llama/9891) leo-pony 2024-10-16 08:51:46 +0800
  • 042e95d92f Vectorize load instructions in dmmv f16 CUDA kernel (llama/9816) agray3 2024-10-14 01:49:08 +0100
  • 81110c0174 ggml : move more prints to the ggml log system (llama/9839) Diego Devesa 2024-10-11 15:34:45 +0200
  • c313723860 rpc : add backend registry / device interfaces (llama/9812) Diego Devesa 2024-10-10 20:14:55 +0200
  • e69b2371e2 musa: add docker image support (llama/9685) R0CKSTAR 2024-10-11 02:10:37 +0800
  • 1531259b2c ggml : fix BLAS with unsupported types (llama/9775) Diego Devesa 2024-10-08 14:21:43 +0200
  • 44bc2767fd ggml : add backend registry / device interfaces to BLAS backend (llama/9752) Diego Devesa 2024-10-07 21:55:08 +0200
  • bd7ace7adc Update building for Android (llama/9672) Andrew Minh Nguyen 2024-10-07 09:37:31 -0700
  • 315364d7de ggml : add metal backend registry / device (llama/9713) Georgi Gerganov 2024-10-07 18:27:51 +0300
  • 80753d4da8 metal : single allocation of encode_async block (llama/9747) Paul Tsochantaris 2024-10-07 13:26:31 +0100
  • 8f9bdca4c4 ggml-alloc : remove buffer_id from leaf_alloc (ggml/987) Daniel Bevenius 2024-10-09 16:40:35 +0200
  • bc763c1d2c
    whisper : backend registry init before model load Georgi Gerganov 2024-10-31 22:53:46 +0200
  • d17cdb3856
    talk-llama : sync llama.cpp Georgi Gerganov 2024-10-31 22:29:22 +0200
  • 9c7653cf05
    sync : ggml Georgi Gerganov 2024-10-31 22:26:28 +0200
  • cc2856458b
    ggml : add AMX backend (llama/8998) Ma Mingfei 2024-10-26 09:43:40 +0300
  • 3481ab5568
    metal : support permuted matrix multiplicaions (llama/10033) Georgi Gerganov 2024-10-25 22:26:15 +0300
  • 8a81531e64
    CUDA: fix insufficient buffer clearing for MMQ (llama/10032) Johannes Gäßler 2024-10-24 14:40:23 +0200
  • 1ac11527ab
    CUDA: fix MMQ for non-contiguous src0, add tests (llama/10021) Johannes Gäßler 2024-10-24 11:09:36 +0200
  • d7ea6cffae
    increase cuda_cpy block size (ggml/996) bssrdf 2024-10-23 14:34:00 -0400
  • 3786b03b0a
    metal : add POOL2D and fix IM2COL (llama/9943) Jun Hee Yoo 2024-10-23 19:33:45 +0900
  • db268981a0
    Adapt to dynamically loadable backends mechanism (llama/9970) leo-pony 2024-10-22 16:16:01 +0800
  • 9b3a2da9ee
    ggml : add asserts for type conversion in fattn kernels (llama/9971) Georgi Gerganov 2024-10-21 16:20:46 +0300
  • 1d0c5773af
    rpc : pack only RPC structs (llama/9959) Radoslav Gerganov 2024-10-21 13:35:40 +0300
  • cd24c266bb
    fix mul_mat_vec_q and *_vec_q error (llama/9939) Neo Zhang Jianyu 2024-10-21 14:26:09 +0800
  • e6d7dbc2f8
    rpc : backend refactoring (llama/9912) Radoslav Gerganov 2024-10-18 14:33:58 +0300
  • 71d0e18012
    Add SYCL Backend registry, device and Event Interfaces (llama/9705) Ouadie EL FAROUKI 2024-10-18 06:46:16 +0100
  • 4d49f588c0
    add amx kernel for gemm (llama/8998) Ma Mingfei 2024-10-18 13:34:36 +0800
  • e2a26601ce
    vulkan : add backend registry / device interfaces (llama/9721) Diego Devesa 2024-10-17 02:46:58 +0200
  • 3017ef0466
    fix: allocating CPU buffer with size 0 (llama/9917) Gilad S 2024-10-17 02:34:22 +0300
  • 24b9e57fc1
    fix: use vm_allocate to allocate CPU backend buffer on macOS (llama/9875) Gilad S 2024-10-17 01:36:51 +0300
  • 3c1d3e4264
    CUDA: fix 1D im2col, add tests (ggml/993) Johannes Gäßler 2024-10-18 09:24:44 +0200
  • eed9509240
    Fix cann compilation error (llama/9891) leo-pony 2024-10-16 08:51:46 +0800
  • fd7ba3344a
    Vectorize load instructions in dmmv f16 CUDA kernel (llama/9816) agray3 2024-10-14 01:49:08 +0100
  • dbb264be0a
    ggml : move more prints to the ggml log system (llama/9839) Diego Devesa 2024-10-11 15:34:45 +0200
  • 5dde62c1d8
    rpc : add backend registry / device interfaces (llama/9812) Diego Devesa 2024-10-10 20:14:55 +0200
  • e493b68ece
    musa: add docker image support (llama/9685) R0CKSTAR 2024-10-11 02:10:37 +0800
  • b1bd75097c
    ggml : fix BLAS with unsupported types (llama/9775) Diego Devesa 2024-10-08 14:21:43 +0200
  • e9ed1a60e4
    ggml : add backend registry / device interfaces to BLAS backend (llama/9752) Diego Devesa 2024-10-07 21:55:08 +0200
  • 456016b2af
    Update building for Android (llama/9672) Andrew Minh Nguyen 2024-10-07 09:37:31 -0700
  • 664ccb765c
    ggml : add metal backend registry / device (llama/9713) Georgi Gerganov 2024-10-07 18:27:51 +0300
  • 5b0a368714
    metal : single allocation of encode_async block (llama/9747) Paul Tsochantaris 2024-10-07 13:26:31 +0100
  • 97b026cc53
    ggml-alloc : remove buffer_id from leaf_alloc (ggml/987) Daniel Bevenius 2024-10-09 16:40:35 +0200
  • 4e10afb5a9
    scripts : sync amx Georgi Gerganov 2024-10-31 22:13:24 +0200
  • aa037a60f3
    ggml : alloc ggml_contexts on the heap (#2525) Georgi Gerganov 2024-10-31 22:00:09 +0200
  • 552419f2c0
    ggml : aligned malloc -> malloc gg/reduce-ctx-use Georgi Gerganov 2024-10-31 21:40:11 +0200
  • 987f3145d0
    ggml : allocate contexts on the heap (v2) Georgi Gerganov 2024-10-31 12:46:20 +0200
  • 9ca474f488
    Merge 82f84e5b2e into 19dca2bb14 Lars Fernhomberg 2024-10-31 18:59:32 +0500
  • 3689d49b81
    whisper : reduce ggml_context usage Georgi Gerganov 2024-10-30 13:39:14 +0200
  • 19dca2bb14
    ci : fix openblas build (#2511) Georgi Gerganov 2024-10-30 12:58:26 +0200
  • 55e422109b
    scripts : add turbo-q8_0 to the benchmark Georgi Gerganov 2024-10-29 19:37:24 +0200
  • 3f020fac9d
    whisper : minor compile warning Georgi Gerganov 2024-10-29 19:27:52 +0200
  • f17dc8dd09 Changed default for MSVC to use AVX Sandro Hanea 2024-10-29 15:53:34 +0100
  • d3f85771ef Fixed No_AVX build on Windows Sandro Hanea 2024-10-29 15:35:39 +0100
  • 1626b73b03
    whisper : move new-segment callback after DTW step (#2515) jettoblack 2024-10-29 02:47:21 -0400
  • 850f7b19d3
    ruby : fix installation test (#2519) KITAITI Makoto 2024-10-29 15:45:37 +0900
  • 2a62723847 Fix test_install Kitaiti Makoto 2024-10-29 04:14:34 +0900
  • d4bc413505
    ruby : add more APIs (#2518) KITAITI Makoto 2024-10-29 02:23:23 +0900
  • 99e7b43cb8 Change prompt text in example Kitaiti Makoto 2024-10-29 01:35:35 +0900
  • 0dd5b5619e [skip ci] Add prompt usage in README Kitaiti Makoto 2024-10-29 01:30:58 +0900
  • 76002a5294 Add progress and abort callback features Kitaiti Makoto 2024-10-29 01:17:39 +0900
  • 820c721094 Add tests for callbacks Kitaiti Makoto 2024-10-29 01:16:53 +0900
  • f316244a03 Add more Whisper::Params attributes Kitaiti Makoto 2024-10-29 01:15:04 +0900
  • 40be1778c7 Add more tests for Whisper::Params Kitaiti Makoto 2024-10-29 01:14:01 +0900