whisper.cpp/.gitignore
Georgi Gerganov b0502836b8
whisper : add full CUDA and Metal offloading (#1472)
* whisper : migrate to ggml-backend

* whisper : fix logit reading

* whisper : fix tensor allocation during load

* whisper : fix beam-search with CUDA

* whisper : free backends + fix compile warning

* whisper : print when CUDA is enabled

* whisper : fix CoreML

* make : clean-up

* talk : fix compile warning

* 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

* whisper : clean-up

* quantize-all : fix

* ggml : im2col opts

* whisper : avoid whisper_model_data wrapper

* whisper : add note that ggml_mul_mat_pad does not work with CUDA

* whisper : factor out graph compute in common function

* whisper : fixes

* whisper : fix UB with measure buffers

* whisper : try to fix the parallel whisper_state functionality (#1479)

* whisper : try to fix the parallel whisper_state functionality

* whisper : fix multi-state Metal

* whisper : free backend instances in whisper_state
2023-11-12 15:31:08 +02:00

57 lines
745 B
Plaintext

*.o
*.a
.cache/
.coreml/
.test/
.vs/
.vscode/
.DS_Store
build/
build-coreml/
build-em/
build-debug/
build-release/
build-rwdi/
build-static/
build-cublas/
build-no-accel/
build-sanitize-addr/
build-sanitize-thread/
# SPM
.build/
.swiftpm
*.metallib
/main
/stream
/command
/talk
/talk-llama
/bench
/quantize
/lsp
arm_neon.h
sync.sh
libwhisper.a
libwhisper.so
compile_commands.json
examples/arm_neon.h
examples/whisper.objc/whisper.objc.xcodeproj/xcshareddata
examples/whisper.objc/whisper.objc.xcodeproj/xcuserdata/
examples/whisper.objc/whisper.objc.xcodeproj/project.xcworkspace/xcuserdata
extra/bench-gg.txt
models/*.mlmodel
models/*.mlmodelc
models/*.mlpackage
bindings/java/.gradle/
bindings/java/.idea/
.idea/
benchmark_results.csv