]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: aaeaa43)
ggml : parallelize FP32 conversion when using BLAS (llama/5045)
authorReinforce-II <redacted>
Mon, 22 Jan 2024 13:15:08 +0000 (21:15 +0800)
committerGeorgi Gerganov <redacted>
Sat, 27 Jan 2024 15:19:51 +0000 (17:19 +0200)
commit0649289f02aec23c6c516a392554ac59c6d6d025
treed8934c62ebbbe321f259b710e400103ccdf7a5a6tree
parentaaeaa43878f179a7c0616b79eed4c9777640fc87commit | diff
ggml : parallelize FP32 conversion when using BLAS (llama/5045)

* make GGML_TASK_INIT phase can be run in multithread

* multithreaded dequantize in mul_mat when using blas library

* minor fixes

* update outdated comment
* fix coding style

* simplify code

Co-authored-by: Georgi Gerganov <redacted>
---------

Co-authored-by: Georgi Gerganov <redacted>
ggml.c diff | blob | history
Packaging of ggerganov/whisper.cpp