GitLab

[VLM] Fix paligemma, fuyu and persimmon with transformers 4.45 : use config.text_config.vocab_size (#8707)

Co-authored-by: litianjian <litianjian@bytedance.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

[Kernel][Triton][AMD] Remove tl.atomic_add from awq_gemm_kernel, 2-5x speedup MI300, minor improvement for MI250 (#8646)

Co-authored-by: Alexei-V-Ivanov-AMD <156011006+Alexei-V-Ivanov-AMD@users.noreply.github.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>

Co-authored-by: Michael Goin <michael@neuralmagic.com>

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>

Co-authored-by: Dipika <dipikasikka1@gmail.com>

Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

Co-authored-by: Yan Ma <yan.ma@intel.com>

[Hotfix][Core][VLM] Disable chunked prefill by default and prefix caching for multimodal models (#8425)

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>