Skip to content

[DO NOT MERGE][ONLY FOR TESTING] Updated chat_sample.py to validate StatefulLLMPipeline #2745

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+17 −5
Open

[DO NOT MERGE][ONLY FOR TESTING] Updated chat_sample.py to validate StatefulLLMPipeline #2745

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
22 changes: 17 additions & 5 deletions samples/python/text_generation/chat_sample.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,20 +18,32 @@ def main():
args = parser.parse_args()

device = args.device
pipe = openvino_genai.LLMPipeline(args.model_dir, device)
pipe = openvino_genai.LLMPipeline(args.model_dir, device, {"ATTENTION_BACKEND" : "SDPA"})

config = openvino_genai.GenerationConfig()
config.max_new_tokens = 100
config.max_new_tokens = 150
config.do_sample = False
config.apply_chat_template = True

pipe.start_chat()
# pipe.start_chat()
while True:
try:
prompt = input('question:\n')
except EOFError:
break
pipe.generate(prompt, config, streamer)
res = pipe.generate([prompt], config, streamer)
print()
perf_metrics = res.perf_metrics
print(f"Stateful pipeline" )
print(f" Generate time: {perf_metrics.get_generate_duration().mean:.2f} ms" )
print(f" TTFT: {perf_metrics.get_ttft().mean:.2f} ms")
print(f" TPOT: {perf_metrics.get_tpot().mean:.2f} ± {perf_metrics.get_tpot().std:.2f} ms/token")
print(f" Throughput: {(1000.0 / perf_metrics.get_tpot().mean):.2f}")
print(f" Num generated token: {perf_metrics.get_num_generated_tokens()} tokens")
print(f" Total iteration number: {len(perf_metrics.raw_metrics.m_durations)}")
print()
print('\n----------')
pipe.finish_chat()
# pipe.finish_chat()


if '__main__' == __name__:
Expand Down
Loading