Georgi Gerganov 933c5bef97 whisper : support ggml_conv with CUDA and Metal (#1473) ...

* ggml : add CUDA support for ggml_conv

* whisper : remove ggml_repeat for conv bias + single backend

* cuda : fix im2col kernel

* metal : add im2col support + mul mat-vec f16 x f16

* bench-all : add q4 models

2023-11-10 22:26:50 +02:00

..

bench-all.sh

whisper : support ggml_conv with CUDA and Metal (#1473)

2023-11-10 22:26:50 +02:00

bench-wts.sh

bench-wts.sh : rename script + add execute permission

2023-03-06 21:02:24 +02:00

bench.py

extra: Add benchmark script implemented in Python (#1298)

2023-09-25 23:45:15 +08:00

convert-all.sh

whisper : add support for large v3 (#1444)

2023-11-07 15:30:18 +02:00

deploy-wasm.sh

Node.js package (#260)

2022-12-12 20:17:27 +02:00

quantize-all.sh

extra : update 'quantize-all.sh' to quantize all downloaded models (#1054)

2023-06-28 22:07:02 +03:00

sha-all.sh

extra : compute SHA of all models files

2022-11-02 18:31:55 +02:00

sync-ggml.sh

cuda : fix HIPBLAS build

2023-11-05 19:41:15 +02:00