]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 682986a)
perplexity : faster HellaSwag via batching (#5017)
authorGeorgi Gerganov <redacted>
Thu, 18 Jan 2024 13:33:01 +0000 (15:33 +0200)
committerGitHub <redacted>
Thu, 18 Jan 2024 13:33:01 +0000 (15:33 +0200)
commitad19812cda4062c9f154ef16315df41fbe6a770a
tree0ce3a8f8e16fb077d614ed2554aff32e82eb61c5tree
parent682986a08eb5cb04865d2e713449f17304d266d8commit | diff
perplexity : faster HellaSwag via batching (#5017)

* perplexity : faster HellaSwag

ggml-ci

* perplexity : clean-up

ggml-ci

* perplexity : no need for decode_helper

ggml-ci

* perplexity : add comments

* perplexity : option to specify max batched tasks via `n_parallel`

* perplexity : remove HellaSwag restruction for n_batch
examples/perplexity/perplexity.cpp diff | blob | history
Packaging of ggml-org/llama.cpp