LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Python

inference-perf

GenAI inference performance benchmarking tool

PythonEmerging

Stars

—

Forks

—

Contributors

8

Last push

7mo ago

Recent commits

Latest commits.

Use 'median' instead of 'p50' in output reports (#201)
8741b33Brendan Slabe10mo ago
Add cnn_dailymail datagen (#196)
d0939fejjk-g10mo ago
Added SGlang server support (#193)
b6687e7Sachin Varghese10mo ago
Remove alpha channel of diagram png to keep presentation consistent in differen browser modes (#199) (#200)
f24d189Qifan Deng10mo ago
Add vllm metrics [preemptions and swapped requests] to prometheus metrics (#197)
3ab904aShuwen Fang10mo ago

Support custom http headers in inference requests (#192)

64eb360Ashok Chandrasekar10mo ago

Rename schedule_accuracy to schedule_delay (#195)

1b241a9jjk-g10mo ago

Defer InferenceAPIData gen to worker procs (#157)

5e1649djjk-g10mo ago

Top contributors

Builders behind this project.