Wentao Ye 4a11ed5bc4 [DSv32/GLM Perf] Skip short prefill topk for dense mha layer, 97.9% kernel level latency reduction (#51298) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2026-08-07 20:30:42 +00:00

..

common

[DSV4] Implement Sequence Parallelism (#46789)

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

deepseek_v4

Support DeepSeek-V4 AMD Quark NVFP4 with emulation kernel (#47972)

2026-08-07 01:19:31 -07:00

deepseek_v32

[DSv32/GLM Perf] Skip short prefill topk for dense mha layer, 97.9% kernel level latency reduction (#51298)

2026-08-07 20:30:42 +00:00

inkling

[Refactor] Remove kernel dead code (#51051)

2026-08-07 01:20:19 -07:00

kimi_k3

[K3 Perf] Optimize k3 dspark fused kv, 4.5~4.6x kernel performance improvement (#50585)

2026-08-07 12:16:11 -07:00

minimax_m3

[Misc] Remove deprecated calculate_kv_scales runtime KV scale calculation (#49389)

2026-08-03 11:15:13 -04:00

__init__.py

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

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