3 people b443c1cc4e [Perf][GLM-5.3-Flash] Use FlashKDA for KDA chunked prefill (1.7-3.8x faster than the Triton chunk path) (#55737) ...

Signed-off-by: Jared Wen <jaredwen@inferact.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-09-14 08:36:19 +00:00

..

common

[5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (#53566)

2026-09-12 00:05:59 -04:00

deepseek_v4

[LoRA] Add LoRA support for DeepSeek-V4 Flash Vision (#55897)

2026-09-13 07:10:54 -07:00

deepseek_v32

[PCP][DCP] Enable PCP+DCP on sparse-MLA models (#56157)

2026-09-12 23:24:44 +00:00

deepseek_v41

[Refactor] Normalize DeepSeek V4.1 model package naming (#56741)

2026-09-13 23:17:50 -07:00

dots3_note

[Performance] Optimize Dots3 NOTE runtime (#53517)

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

glm5next

[Perf][GLM-5.3-Flash] Use FlashKDA for KDA chunked prefill (1.7-3.8x faster than the Triton chunk path) (#55737)

2026-09-14 08:36:19 +00:00

hy_v4

[ROCm][CI] Enable HY-V4 model initialization on ROCm (#54405)

2026-09-07 20:55:44 -05:00

inkling

[3/N][warmup][DSv4] Migrate FA4 MLA and shared CuTeDSL kernels (#53565)

2026-09-07 09:36:35 -04:00

kimi_k3

[ROCm][Kimi-K3] Fix non-contiguous state_indices crash and GPU-sync assert in fused KDA/MLA prefill (#56526)

2026-09-11 20:17:39 -05:00

minimax_m3

[ROCm][Perf] Tune MiniMax-M3 decode top-k for short contexts (#55235)

2026-09-13 21:36:27 -05:00

qwen4_exp

[Qwen4Exp] Support UVA PLE-offload and Engram tensor parallelism (#54371)

2026-09-09 07:32:34 -07:00

__init__.py

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

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