PR #3112 Bug Fix: Sliding Window Attention

(fix) sliding window attention

mht-sharma committed 1 year ago

(fix) flashinfer

mht-sharma committed 1 year ago

(typo) collection link

mht-sharma committed 1 year ago

Add window_size_left param ipex rocm

mht-sharma committed 1 year ago

Update window size rocm flash decoding

mht-sharma committed 1 year ago

fix: bump snapshots and improve exceed window test case

drbh committed 1 year ago

feat: add tests for image types and remove alpha from png

drbh committed 1 year ago

Upgrading `from_env` to get token from file when necessary + fix

Narsil committed 1 year ago

fix: add pillow dependency and bump lock+requirements

drbh committed 1 year ago

fix: bump org name in gemma3 test

drbh committed 1 year ago

Fix qwen2.

Narsil committed 1 year ago

text-generation-inference Bug Fix: Sliding Window Attention #3112 Merged