]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
Fix more int overflow during quant (PPL/CUDA). (llama/6563)
authorDAN™ <redacted>
Sun, 28 Apr 2024 22:38:44 +0000 (18:38 -0400)
committerGeorgi Gerganov <redacted>
Mon, 13 May 2024 08:02:26 +0000 (11:02 +0300)
commitb574646d754b4abd54c4df544e648f5232fd00be
treed2e580920837509dd3eeff4f2a1db6de902013a8
parent388c3462a6c38a09e403c4b2b061cd5f154edf52
Fix more int overflow during quant (PPL/CUDA). (llama/6563)

* Fix more int overflow during quant.

* Fix some more int overflow in softmax.

* Revert back to int64_t.
ggml-cuda/convert.cu
ggml-cuda/softmax.cu