Woosuk Kwon b09bd69b5b [Model][NVIDIA] Route DSA models to the CUDA non-compiled path (#52861)

2026-08-19 00:13:52 -07:00

..

common

[DSV4] Implement Sequence Parallelism (#46789)

2026-08-01 10:22:33 -07:00

deepseek_v4

Revert DSv4 eager workspace reuse (#52836)

2026-08-18 17:02:59 -07:00

deepseek_v32

[Model][NVIDIA] Route DSA models to the CUDA non-compiled path (#52861)

2026-08-19 00:13:52 -07:00

dots3_note

[Bugfix] Disable sequence parallelism for Dots3 NOTE (#52172)

2026-08-13 22:13:00 +08:00

inkling

[MM] Keep more metadata tensors on CPU (#52827)

2026-08-18 19:56:33 -07:00

kimi_k3

[ROCm][Perf] Enable fused KDA decode on gfx942 (MI325X) (#52293)

2026-08-18 18:01:00 +00:00

minimax_m3

[MOE] Standardize and abstract fused shared expert optimization selection (#51695)

2026-08-18 12:56:56 -04:00

__init__.py

[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)

2026-05-18 19:50:02 -07:00