[Refactor] Remove multiple dead codes (#50285)

Wentao Ye committed 3 months ago

[Bugfix] Remove bad startup assertion (#50869)

Benjamin Chislett committed 3 months ago

[CI] Mooncake PD integration tests (#46844)

Nicolò Lucchesi committed 3 months ago

docs: document `reasoning_content` output removal as a breaking client change (#50624)

Fede Kamelhar committed 3 months ago

[Model] Add K-EXAONE-2.0-750B-A37B (#50524)

Kyungmin Lee committed 3 months ago

Support quantized DSpark Markov heads (#50424)

Andrii Skliar committed 3 months ago

[CI] KimiLinear PD in nightlies (#50266)

Nicolò Lucchesi committed 3 months ago

[CPU] Fix torch.compile crash from torch.accelerator.synchronize on CPU-only hosts (#49960)

Ganesh R committed 3 months ago

[UX] remove torch compile warning when using breakable cudagraph (#50750)

Jiangyun Zhu committed 3 months ago

[CI] And PPL test for multimodal generation models (#50839)

wang.yuqi committed 3 months ago

[CPU] Refine CPU kernel dispatch (#50801)

Li, Jiang committed 3 months ago

K3: Move LatentMoERunner (#50678)

Jee Jee Li committed 3 months ago

fix: remove stray duplicate from serving benchmark config (#46870)

Christopher Miyai committed 3 months ago

[Perf] Speed up multimodal placeholder and token-match scanning (#50716)

Hareesh Gali committed 3 months ago

fix(security): classify DeepStream as GPU backend and enforce pixel limits (#50755)

Juan Pérez de Algaba committed 3 months ago

Shard the K3 Latent-MoE up-projection on large batches (#50383)

Jee Jee Li committed 3 months ago

[CPU] Migrate unquantized MoE to the modular-kernel experts structure (#50133)

Li, Jiang committed 3 months ago

[Frontend] Require cache_salt to be non-empty via schema (#50816)

Cyrus Leung committed 3 months ago

[XPU] [Linear] add torch as xpu linear backend (#49664)

zofia committed 3 months ago

[INC] fix w4a4 model (#50807)

Qiming Zhang committed 3 months ago