auto-round
Implement shard parallelism configuration and update documentation
#1942
Merged
Merged
Implement shard parallelism configuration and update documentation #1942
chensuyue
merged
11 commits into
main
from
xinhe/6-23
Implement shard parallelism configuration and update documentation
029509a1
fix pylint
5f5e8ee4
Implement shard processing with multiprocessing for improved performance
45d37870
Merge branch 'main' into xinhe/6-23
cd922ebc
fix vllm issue that embed should not be included
ad83947c
clear memory
3d6c22e3
Add model_type parameter to shard processing and implement quantizati…
11c038f8
Add model-free parallelism benchmarks to step-by-step documentation
d9028c39
Refactor MXFP tensor handling and add device fallback for dequantization
6cd70955
fix CI
136ab0ac
lkk12014402
approved these changes
on 2026-06-24
changwangss
approved these changes
on 2026-06-24
wenhuach21
commented
on 2026-06-24
address PR1942 review comments
15e008c3
Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
Login to write a write a comment.
Login via GitHub