f842d31171
whisper : calculate mel spectrogram directly into a ggml_tensor ( #2208 )
...
* whisper : calculate mel spectrogram directly into a ggml_tensor
* whisper : remove unused temp buffer from state
* whisper : fix not initializing wstate.embd_enc
2024-06-06 16:20:46 +03:00
ffef323c4c
whisper : add CUDA-specific computation mel spectrograms ( #2206 )
...
* whisper : use polymorphic class to calculate mel spectrogram
* whisper : add cuda-specific mel spectrogram calculation
* whisper : conditionally compile cufftGetErrorString to avoid warnings
* build : add new files to makefile
* ruby : add new files to conf script
* build : fix typo in makefile
* whisper : suppress cub warning for deprecated C++ std in whisper-mel-cuda
2024-06-04 09:32:23 +03:00
af5833e298
whisper : remove speed_up and phase_vocoder* functions ( #2198 )
...
* whisper : fix cast warning
* whisper : remove phase_vocoder functions, ref #2195
* whisper : remove speed_up from whisper_full_params, closes #2195
2024-05-31 11:37:29 +03:00
b87494bb8f
readme : add conan badge ( #2196 )
...
* Add conan badge
* Fix markdown formating
2024-05-30 15:43:28 +03:00
ad130431aa
readme : add install instructions for Conan ( #2189 )
2024-05-30 15:06:15 +03:00
e130b66642
whisper: use global cache for sin/cos vals and Hann window ( #2194 )
...
- also rename Hanning to Hann as it's named after Julius von Hann
as per Wikipedia
2024-05-29 19:09:21 +03:00
c7b6988678
release : v1.6.2
2024-05-27 10:35:09 +03:00
05042a782d
Revert "whisper : remove extra backend instance (huh?)" ( #2182 )
...
This reverts commit 4caa64b73e
2024-05-27 10:20:25 +03:00
a7dc2aab16
server : fix typo ( #2181 )
...
A simple comment typo, PR can be dismissed
2024-05-25 10:46:22 +03:00
22d46b7ba4
ruby : update bindings ( #2154 )
...
* update library files
* update whispercpp
* not needed for gem
2024-05-22 23:02:52 +03:00
c10db6ea28
release : v1.6.1
2024-05-21 18:44:37 +03:00
1b51fdf170
examples : add support for decoding input with ffmpeg (Linux) ( #2133 )
...
- search for ffmpeg libs/headers at cmake time
- added ffmpeg-transcode.cpp into libcommon if ffmpeg on
- hooked ffmpeg trancoding in common read_wav(...)
- passed test:
./main -m ggml-base.en.bin -f samples/jfk.mp3
2024-05-21 18:31:41 +03:00
adee3f9c1f
node : add flash_attn param ( #2170 )
2024-05-20 09:08:48 +03:00
4798be1f9a
ci: Update build.yml to suppress warnings about node.js versions ( #2166 )
...
* Update actions to suppress warnings about old node.js
https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/
* Update actions/upload-artifact, specify android cmdline-tools-version
* Use java 20
gradle 8.1 complains against 21
https://docs.gradle.org/current/userguide/compatibility.html
2024-05-19 11:49:26 +03:00
08981d1bac
release : v1.6.0
2024-05-15 09:59:48 +03:00
7094ea5e75
whisper : use flash attention ( #2152 )
...
* whisper : use flash attention in the encoder
* whisper : add kv_pad
* whisper : remove extra backend instance (huh?)
* whisper : use FA for cross-attention
* whisper : use FA for self-attention
* whisper : simplify encoder FA
* whisper : add flash_attn runtime parameter
* scripts : add bench log
* scripts : add M1 Pro bench log
2024-05-15 09:38:19 +03:00
9d5771ae43
talk-llama : reject runs without required arguments ( #2153 )
...
* Extended talk-llama example to reject runs without required arguments.
Print warning and exit if models are not specified on the command line.
* Update examples/talk-llama/talk-llama.cpp
* Update examples/talk-llama/talk-llama.cpp
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-05-14 21:32:41 +03:00
f56b8305c4
sync : ggml
2024-05-14 19:16:32 +03:00
1056ad762c
metal : support FA without mask + add asserts (llama/7278)
...
* ggml : fa without mask + add asserts
ggml-ci
* metal : support non-contiguous KV
ggml-ci
2024-05-14 19:16:29 +03:00
c451080c8b
ggml : add RPC backend (llama/6829)
...
* ggml : add RPC backend
The RPC backend proxies all operations to a remote server which runs a
regular backend (CPU, CUDA, Metal, etc).
* set TCP_NODELAY
* add CI workflows
* Address review comments
* fix warning
* implement llama_max_devices() for RPC
* Address review comments
* Address review comments
* wrap sockfd into a struct
* implement get_alignment and get_max_size
* add get_device_memory
* fix warning
* win32 support
* add README
* readme : trim trailing whitespace
* Address review comments
* win32 fix
* Address review comments
* fix compile warnings on macos
2024-05-14 19:16:29 +03:00
8e7c22fbdb
rm wait() (llama/7233)
2024-05-14 19:16:29 +03:00
e57e95eb0d
CUDA: add FP32 FlashAttention vector kernel (llama/7188)
...
* CUDA: add FP32 FlashAttention vector kernel
* fixup! CUDA: add FP32 FlashAttention vector kernel
* fixup! fixup! CUDA: add FP32 FlashAttention vector kernel
* fixup! fixup! fixup! CUDA: add FP32 FlashAttention vector kernel
2024-05-14 19:16:29 +03:00
130f43e4b8
scripts : sync ggml-rpc
2024-05-14 19:15:35 +03:00
d8356a1cc2
whisper : fix model path encoding in windows ( #2086 )
...
* fix: model path encoding in windows
* fix: convert model path to wide string only for MSVC compiler
2024-05-14 09:43:41 +03:00
4ef8d9f44e
server : return utf-8 ( #2138 )
2024-05-13 15:33:46 +03:00
3928dbd206
node : add audio_ctx and audio buffer params ( #2123 )
...
* node : add audio_ctx param
* node : support passing audio buffer directly
* node : parse audio_ctx in index.js
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-05-13 15:22:23 +03:00
2ced6f0742
cmake : fix HIP/ROCm build ( #2102 )
2024-05-13 15:18:43 +03:00
30f73109b8
node : add additional params ( #2000 )
...
* Add additional params to addon.node
* Add comma_in_time as parameter
* Fix tests
2024-05-13 15:15:43 +03:00
17fa62d3d3
js : remove un-needed request header from fetchRemote ( #2119 )
2024-05-13 15:13:19 +03:00
1da5edcde0
cmake : fix metal embed sources path ( #2110 )
2024-05-13 15:09:59 +03:00
0bb05b113d
main : dont print timings with --no-prints ( #2108 )
...
Signed-off-by: Daniel Ziegenberg <daniel@ziegenberg.at >
2024-05-13 15:00:19 +03:00
f141b2b938
main : add options for temperature control ( #2088 )
...
Add two options:
```
-tp, --temperature N [0.00 ] The sampling temperature, between 0 and 1
-tpi, --temperature-inc N [0.20 ] The increment of temperature, between 0 and 1
```
The sampling temperature, between 0 and 1. Higher values like 0.8 will
make the output more random, while lower values like 0.2 will make it
more focused and deterministic. If set to 0, the model will use log
probability to automatically increase the temperature until certain
thresholds are hit.
Signed-off-by: Daniel Ziegenberg <daniel@ziegenberg.at >
2024-05-13 14:59:44 +03:00
2b434c449e
whisper : switch back to F32 mask ( #0 )
2024-05-13 14:43:43 +03:00
e93081f83f
whisper.android : update example, add field to print timestamp ( #2072 )
2024-05-13 14:30:03 +03:00
b6bbce4ae9
cmake : fix json INTERFACE library ( #2069 )
2024-05-13 14:29:39 +03:00
7705dc52da
main : fix double quote escaping in csv output ( #2090 )
2024-05-13 11:55:32 +03:00
e6acaf9d91
metal : tune soft_max number of threads ( #0 )
2024-05-13 11:02:26 +03:00
2c81e6fd51
whisper : remove old flash attn code ( #0 )
2024-05-13 11:02:26 +03:00
9506267ce5
ggml : try fix ppc64 ( #0 )
2024-05-13 11:02:26 +03:00
fbeb80b5f0
ggml : remove oboslete alibi code (skipme) ( #0 )
2024-05-13 11:02:26 +03:00
3fa7d29876
talk-llama : sync llama.cpp
2024-05-13 11:02:26 +03:00
fe179ae0cc
sync : ggml
2024-05-13 11:02:26 +03:00
40aeeeecc4
ggml : optimize for ppc64le using VSX intrinsics (ggml/784)
...
* optimize for ppc64le using VSX intrinsics
* 1. code clean up by removing comments about overflow concern.
2. fix typo in suffix of scaling.
* Continue to fix typo in suffix of scaling for QK_K <> 256
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2024-05-13 11:02:26 +03:00
5a863fbe18
metal : fix indent (ggml/0)
2024-05-13 11:02:26 +03:00
91c646c61d
ggml : restore sigmoid decl order (ggml/0)
2024-05-13 11:02:26 +03:00
accada542a
ggml : resolve merge (ggml/0)
...
ggml-ci
2024-05-13 11:02:26 +03:00
e54329da7b
ggml : full ALiBi support (llama/7192)
...
* ggml : full ALiBi support
* ggml : update ggml_soft_max_ext() CUDA, SYCL
* ggml : ggml_flash_attn_ext() support ALiBi (CPU)
* ggml : ggml_flash_attn_ext() support ALiBi (Metal)
* ggml : fix warning
* ggml : ggml_flash_attn_ext() support ALiBi (CUDA)
ggml-ci
* ggml : fix assert message
* vulkan : add dev notes
* ggml : require mask when using ALiBi
ggml-ci
* convert : fix convert for refact models
2024-05-13 11:02:26 +03:00
284fac39fb
metal : fix flash attention kernel requirements (llama/7169)
...
* metal : fix flash attention kernel requirements
ggml-ci
* metal : fix ggml_metal_supports_op
ggml-ci
2024-05-13 11:02:26 +03:00
fe454b8d9e
Minor arithmetic improvement to mmvq wrapper kernel (llama/7172)
2024-05-13 11:02:26 +03:00
c114b75aee
Vulkan Bugfixes and Improvements (llama/7084)
...
* Modify mat mat mul shader for mul_mat_id, modify mat vec mul shaders for single call batch operation
* Further work towards MoE, disabled for now
* Disable MoE code (not ready yet), fix a number of bugs in shaders and Vulkan code
* Add softmax with f16 mask and pos buffer support
* Disable mul_mat_id shaders for now
* Fix flake8
* Fix validation errors caused by empty buffers on larger batch sizes
2024-05-13 11:02:26 +03:00
