* ggml : disable fast-math for Metal (cmake build only)
ggml-ci
* metal : fix Metal API debug warnings
* cmake : add -fno-inline for Metal build (llama/4545)
* metal : fix API debug warnings
* metal : fix compile warnings
* metal : use uint64_t for strides
* cmake : rename option to LLAMA_METAL_SHADER_DEBUG
* metal : fix mat-vec Q8_0 kernel for BS > 1
* metal : normalize mat-vec kernel signatures
* cmake : respect LLAMA_QKK_64 option
* metal : fix mat-vec Q4_K kernel for QK_K == 64
* metal : optimizing ggml_mul_mat_id (wip)
* metal : minor fix
* metal : opt mul_mm_id
* ggml : disable fast-math for Metal (cmake build only)
ggml-ci
* metal : fix Metal API debug warnings
* cmake : add -fno-inline for Metal build (llama/4545)
* metal : fix API debug warnings
* metal : fix compile warnings
* metal : use uint64_t for strides
* cmake : rename option to LLAMA_METAL_SHADER_DEBUG
* metal : fix mat-vec Q8_0 kernel for BS > 1
* metal : normalize mat-vec kernel signatures
* cmake : respect LLAMA_QKK_64 option
* metal : fix mat-vec Q4_K kernel for QK_K == 64
ggml-ci
* feat: add avx_vnni based on intel documents
* ggml: add avx vnni based on intel document
* llama: add avx vnni information display
* docs: add more details about using oneMKL and oneAPI for intel processors
* docs: add more details about using oneMKL and oneAPI for intel processors
* docs: add more details about using oneMKL and oneAPI for intel processors
* docs: add more details about using oneMKL and oneAPI for intel processors
* docs: add more details about using oneMKL and oneAPI for intel processors
* Update ggml.c
Fix indentation upgate
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Fix for problem:
"""
RuntimeError: Aborted(Stack overflow! Stack cookie has been overwritten at 0x12be2b10, expected hex dwords 0x89BACDFE and 0x2135467, but received 0x00000000 0x00000000)
"""
That appears when executing the WASM example with the newer versions.
* build: add dockerfile for ci
* ci: add action to build/push docker image
* fix: lowercase repository to fix ci
* ci: update cuBLAS flag
* build: install curl and ffmped in image
* docs: add docker section
* fix: improve args check when download model
Since we use prefetchVirtualMemory we specify we target win 8 or above, otherwise other compilers will refuse to use the prefetchVirtualMemory api, (I understand you are loading it dynamically but the header definition has this limitation)
- The code comes from examples/main
- The output mimetype is set to text/vtt
Example usage:
```shell
curl 127.0.0.1:8080/inference \
-H "Content-Type: multipart/form-data" \
-F file="@samples/jfk.wav" \
-F temperature="0.2" \
-F response-format="vtt"
```
This commit adds a support of .srt format to Whisper server. The code is
effectively backported from examples/main. The output mimetype is set to
application/x-subrip as per https://en.wikipedia.org/wiki/SubRip.
Example usage:
curl 127.0.0.1:8080/inference \
-H "Content-Type: multipart/form-data" \
-F file="@<file-path>" \
-F temperature="0.2" \
-F response-format="srt"
* server : automatically convert audio on the server
* server : remove rebundant comments
* server : automatic conversion refactor
* server : update server readme
* server : remove unnecessary comments and tabs
* server : put back remove calling
* server : apply suggestions from code review
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* server : check ffmpeg before the server lunch
* server : fix indentation
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* server : fix function typo calling
* server : fix function typo calling
* server : add warning in readme
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
