Skip to content

update to docker image 2.2.1 #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 18, 2025
Merged

update to docker image 2.2.1 #13

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion benchmarks/run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ def get_file_dir():


def docker_init(node):
tag = "amperecomputingai/llama.cpp:2.0.0"
tag = "amperecomputingai/llama.cpp:2.2.1"
if subprocess.run(
["docker", "pull", tag]).returncode != 0:
print("Docker pull process failed!")
Expand Down
6 changes: 3 additions & 3 deletions benchmarks/utils/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ def summarize_results(logs_dir, args, start, finish):
ttfts = []
tg_lats = []
for n in range(args.num_processes):
results = open(f"{logs_dir}/log_{n}", "r").readlines()[-9].split("|")
results = open(f"{logs_dir}/log_{n}", "r").readlines()[5].split("|")
prompt_size = int(results[1])
assert prompt_size == args.prompt_size
tokens_generated = int(results[2])
Expand Down Expand Up @@ -142,11 +142,11 @@ def main():
if mem_place == "none":
cmd = ["numactl", f"--physcpubind={gen_threads_config(args.num_threads, n)}",
"/llm/llama-batched-bench", "-m", args.model, "-c", str(args.kv_cache), "-b", "2048", "-ub", "512", "-npp", str(args.prompt_size), "-ntg", str(TOKENS),
"-npl", str(args.batch_size), "-t", str(args.num_threads), "-tb", str(args.num_threads), "-td", str(args.num_threads)]
"-npl", str(args.batch_size), "-t", str(args.num_threads), "-tb", str(args.num_threads)]
else:
cmd = ["numactl", f"--physcpubind={gen_threads_config(args.num_threads, n)}",str(mem_place),
"/llm/llama-batched-bench", "-m", args.model, "-c", str(args.kv_cache), "-b", "2048", "-ub", "512", "-npp", str(args.prompt_size), "-ntg", str(TOKENS),
"-npl", str(args.batch_size), "-t", str(args.num_threads), "-tb", str(args.num_threads), "-td", str(args.num_threads)]
"-npl", str(args.batch_size), "-t", str(args.num_threads), "-tb", str(args.num_threads)]

else:
print("FAIL: batched-bench not found!")
Expand Down