-
Notifications
You must be signed in to change notification settings - Fork 17
Add offline perf ci #181
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.
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
Add offline perf ci #181
Conversation
940e6ee
to
dfd99a9
Compare
Number of devices: 8 |
Is this PR ready to review? |
60919fd
to
5b370db
Compare
Offline benchmark numbersModel: meta-llama/Meta-Llama-3-8B-InstructBatch size: 128Quantize: False
|
@FanhaiLu1 Now it's ready. The goal is for it to automatically generate the offline benchmark |
Offline benchmark numbersModel: meta-llama/Meta-Llama-3-8B-InstructBatch size: 128Quantize: False
|
benchmarks/run_offline.py
Outdated
@@ -92,7 +92,8 @@ def main(argv): | |||
|
|||
decode_state = engine.init_decode_state() | |||
profiler_started = False | |||
for batch, _ in MAXTEXT_PREFILL.items(): | |||
for exp in range(4, 11): | |||
batch = 2**exp |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The run_prefill_time function argument is seqlen, should we rename batch to seqlen?
Offline benchmark numbersModel: meta-llama/Meta-Llama-3-8B-InstructBatch size: 128Quantize: False
|
Uh oh!
There was an error while loading. Please reload this page.