llama.cpp
kompute : llama-bench support and ggml_cpu_has_kompute()
#5226

Merged

kompute : llama-bench support and ggml_cpu_has_kompute() #5226

cebtenzzre merged 2 commits into master from ceb/kompute-llama-bench

kompute : llama-bench support and ggml_cpu_has_kompute()

e3b420a4

cebtenzzre requested a review from

ggerganov 2 years ago

slaren approved these changes on 2024-01-30

llama : remove obsolete set of n_threads=1

3536cf60

cebtenzzre removed review request from

ggerganov 2 years ago

cebtenzzre merged e8dc55d0 into master 2 years ago

cebtenzzre deleted the ceb/kompute-llama-bench branch 2 years ago

Reviewers

slaren

Assignees

No one assigned

Labels

None yet

Milestone

No milestone