[Serving][Benchmark] Add benchmark code for serving #69
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Currently prompts are sampled from ShareGPT, I am thinking adding more prompt workloads. |
zhangjian94cn
pushed a commit
to zhangjian94cn/llm-on-ray
that referenced
this pull request
Feb 4, 2024
* support more models in finetune * modify dockerfile * fix bug caused by accelerate upgrade * add llama2 * fix error * fix error * test * fix error * support_lora_finetune * fix error * remove bin before lora test * fix * update
carsonwang
reviewed
Feb 5, 2024
|
Added support for ipex prompt.json dataset, will continue to add
|
xwu99
force-pushed
the
add-benchmark-serving
branch
from
2baaeb2
to
d0b5659
Compare
KepingYan
reviewed
Mar 4, 2024
benchmarks/benchmark_serving.py
Outdated
| """ | ||
| tasks: List[asyncio.Task] = [] | ||
| progress_bar = tqdm(total=len(input_requests)) if progress else None | ||
| async for request in get_request(input_requests, request_rate): |
There was a problem hiding this comment.
Maybe we need to make a deep copy of the parameter config in this loop.
benchmarks/benchmark_serving.py
Outdated
Comment on lines
227
to
231
| # Use sample output_len if max_new_tokens not specified | ||
| if "max_new_tokens" in config: | ||
| output_len = config["max_new_tokens"] | ||
| else: | ||
| config["max_new_tokens"] = output_len |
There was a problem hiding this comment.
Or make a deep copy of the config parameters here. Otherwise, when passing through line 231 for the first time, the value of config will become {'max_new_tokens': 37}, so that the output_len will be 37 every time in the future. This is why total_time is reduced a lot
There was a problem hiding this comment.
good catch, pls feel free to fix this.
|
replaced with #163 and already merged. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
closes #68