llama.cpp
sampling: reuse token data buffer in llama_sampler_sample
#18365

Merged

sampling: reuse token data buffer in llama_sampler_sample #18365

ggerganov merged 3 commits into ggml-org:master from JayZenith:fix-sampling-alloc

JayZenith requested a review from

ggerganov 64 days ago

JayZenith closed this 64 days ago

JayZenith reopened this 64 days ago

ggerganov approved these changes on 2025-12-29

JayZenith force pushed from 7ab07509 to f40f43a7 60 days ago

JayZenith force pushed from f40f43a7 to 517bb736 60 days ago

JayZenith force pushed from 517bb736 to 515d8dc7 60 days ago

sampling: reuse token data buffer in llama_sampler_sample

e19fb5f1

move cur buffer before timing section, after samplers

61c2d17e

JayZenith force pushed from 515d8dc7 to 61c2d17e 60 days ago

minor : fix build

08331ddf

ggerganov merged c32fa21d into master 59 days ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

None yet

Milestone

No milestone