llama.cpp
llama : llama_perf + option to disable timings during decode
#9355

Merged

llama : llama_perf + option to disable timings during decode #9355

ggerganov merged 9 commits into master from gg/llama-perf

ggerganov force pushed 1 year ago

llama : llama_perf + option to disable timings during decode

471e7e1e

common : add llama_arg

ade52b6c

ggerganov force pushed to ade52b6c 1 year ago

ggerganov marked this pull request as ready for review 1 year ago

ngxson commented on 2024-09-08

Merge branch 'master' into gg/llama-perf

6cce78c2

ggerganov added breaking change

ggerganov commented on 2024-09-10

ggerganov requested a review from

slaren 1 year ago

ggerganov requested a review from

ngxson 1 year ago

ngxson approved these changes on 2024-09-10

ngxson commented on 2024-09-10

Update src/llama.cpp

fd465353

slaren commented on 2024-09-10

perf : separate functions in the API

f42de242

github-actions added examples

slaren commented on 2024-09-11

perf : safer pointer handling + naming update

7362f288

Merge branch 'master' into gg/llama-perf

44f02185

minor : better local var name

f35e9b87

perf : abort on invalid sampler pointer

444b757b

slaren approved these changes on 2024-09-13

ggerganov merged 0abc6a2c into master 1 year ago

ggerganov deleted the gg/llama-perf branch 1 year ago

RatStar811 approved these changes on 2025-12-29

Reviewers

slaren

ngxson

RatStar811

Assignees

No one assigned

Labels

breaking change examples

Milestone

No milestone

llama.cpp llama : llama_perf + option to disable timings during decode #9355 Merged

llama : llama_perf + option to disable timings during decode #9355

llama.cpp
llama : llama_perf + option to disable timings during decode
#9355

Merged