Wei ZhaoandOpenAI Codex 16328c7a77 [Perf] Kimi K3 nvfp4 Align in_proj weights by 128 to avoid elementwise copy (#55242) ...

Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>

2026-09-05 10:46:47 +08:00

..

common

[Perf] Prefetch the weight before the PDL wait in fused_q_kv_rmsnorm (#55020)

2026-09-03 15:40:16 -07:00

deepseek_v4

[Bugfix][Quantization] Register Quark per-block FP8 scales as weight_scale (#54770)

2026-09-05 10:44:24 +08:00

deepseek_v32

[Bugfix][DCP] Materialize prefill keys on non-owner ranks (#54908)

2026-09-04 02:12:07 +00:00

dots3_note

[Performance] Optimize Dots3 NOTE runtime (#53517)

2026-08-31 00:05:18 -07:00

glm5next

[Bugfix][Docs] Package glm5next nvidia subtree and fix its docstrings (#55214)

2026-09-03 21:25:26 -07:00

hy_v4

[Hy4] support Hy4-preview model (#54160)

2026-08-29 12:07:28 +08:00

inkling

[Model Runner V2] batch-sharded sample (#50465)

2026-08-24 15:49:57 -07:00

kimi_k3

[Perf] Kimi K3 nvfp4 Align in_proj weights by 128 to avoid elementwise copy (#55242)

2026-09-05 10:46:47 +08:00

minimax_m3

[ROCm][Perf] Optimize MiniMax-M3 decode indexer and top-k (#54682)

2026-09-03 13:20:18 -07:00

qwen4_exp

[Qwen3.8-Flash-Next] Improve QSA sparse GQA for prefill and short-ctx decode (#54873)

2026-09-04 06:08:02 -07:00

__init__.py

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

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