pullrequests Search Results · bucket language:JavaScript language:Java language:Python language:JavaScript language:JavaScript
Filter by
1.1M results
dependencies
python
dependabot[bot]
Summary
Under DP attention, extend steps pad each rank to the raw max token count first, then the shim pads again to a bucket.
The raw max changes almost every step, so the eager pads and the idle ...
run-ci
tpu
junyanxu
yuzhongw-nvidia
dependencies
python:uv
dependencies
python:uv
...
How it solves it:
- The window and pools are keyed by provider bucket: the organization of the deployment that serves the call plus its
model class
- Admission moves to the router stage that ...
sjawhar-agent[bot]
quittle
ez2appbug
dependencies
documentation
enhancement
python
dependencies