[Misc] add gpu_memory_utilization arg #5079
Merged
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
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
sroy745
reviewed
May 29, 2024
| @@ -211,5 +212,11 @@ def run_to_completion(profile_dir: Optional[str] = None): | |||
| type=str, | |||
| default=None, | |||
| help='Path to save the latency results in JSON format.') | |||
| parser.add_argument('--gpu-memory-utilization', | |||
There was a problem hiding this comment.
Wondering if we want to expose max-model-len as well in the args. We are doing that in the benchmark_througput ( https://sourcegraph.com/github.com/vllm-project/vllm/-/blob/benchmarks/benchmark_throughput.py?L301) and wondering if we should add it here as well since that is another parameter to tune for this error?
simon-mo
approved these changes
May 29, 2024
blinkbear
pushed a commit
to blinkbear/vllm
that referenced
this pull request
May 29, 2024
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
dtrifiro
pushed a commit
to opendatahub-io/vllm
that referenced
this pull request
May 31, 2024
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
robertgshaw2-neuralmagic
pushed a commit
to neuralmagic/nm-vllm
that referenced
this pull request
Jun 8, 2024
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
joerunde
pushed a commit
to joerunde/vllm
that referenced
this pull request
Jun 17, 2024
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
robertgshaw2-neuralmagic
pushed a commit
to neuralmagic/nm-vllm
that referenced
this pull request
Jul 14, 2024
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
Temirulan
pushed a commit
to Temirulan/vllm-whisper
that referenced
this pull request
Sep 6, 2024
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
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.
For Larger models like: meta-llama/Meta-Llama-3-70B It throws
ValueError: The model's max seq len (8192) is larger than the maximum number of tokens that can be stored in KV cache (4688). Try increasing
gpu_memory_utilizationor decreasingmax_model_lenwhen initializing the engine.It's required to specify gpu_memory_utilization to successfully run the benchmark.