Jaden Mathias d848c4ed3d [ROCm][Triton] Migrate Kimi-K3 kernels from make_block_ptr to tensor … (#58769) ...

Signed-off-by: JadenMathias <jaden.mathias@amd.com>

2026-10-01 13:41:41 -05:00

..

common

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

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

deepseek_v4

[BugFix][Multimodal] Pick worst-case DeepSeek-V4 VL dummy image size (#59271) (#59373)

2026-09-30 15:09:11 +00:00

deepseek_v32

[GLM 5.3 Perf] Skip qlnorm calculation for MHA, 4.4~7.7% E2E TTFT Improvement (#58845)

2026-10-01 15:13:57 +08:00

deepseek_v41

[Perf][DSv4.1] Faster Engram host lookups: sorted rows, inline big lookups (#59327)

2026-10-01 11:54:44 +08:00

dots3_note

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

glm5next

[XPU] Dispatch nn.LayerNorm to fused SYCL kernel via CustomOp (#57172)

2026-09-30 12:19:33 +00:00

hy_v4

[XPU] Dispatch nn.LayerNorm to fused SYCL kernel via CustomOp (#57172)

2026-09-30 12:19:33 +00:00

inkling

[Bugfix][Spec Decode] Per-module LM heads for multi-layer MTP on Model Runner V2 (#58921)

2026-10-01 01:09:14 -07:00

kimi_k3

[ROCm][Triton] Migrate Kimi-K3 kernels from make_block_ptr to tensor … (#58769)

2026-10-01 13:41:41 -05:00

minimax_m3

[Bugfix][PP][Spec Decode] MiniMax-M3 EAGLE3 aux-state relay at PP > 1 and per-stage FlashInfer autotune (#57197)

2026-10-01 01:14:24 +04:00

qwen4_exp

[Core] Remove deprecated mamba_cache_mode "all" (#58997)

2026-10-01 02:59:37 -07:00

__init__.py

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

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