Open Models Almanac
Methodssoftware implementationkernel & quantization library

methods · software implementation

kernel & quantization library

25 methods filed at this node or below it, from the sources of 15 models.

In this branch 25

Everything filed at this node or below it, with one collapsible heading per child node.

filed here 25

AngelSlim used · 2 sources · 2 quotes
FlashInfer used · 2 sources · 2 quotes
FlashInfer NVLinkOneSided all-to-all used · 2 sources · 2 quotes
FlashInfer TensorRT-LLM backend used · 2 sources · 2 quotes
MegaMoE used · 2 sources · 3 quotes
NVIDIA Model-Optimizer used · 2 sources · 2 quotes
deepseek-recipe optional · 2 sources · 2 quotes
18 single mentions
AITER gfx950 DSA indexer kernels default · 1 source · 1 quote
AITER sparse MLA decode kernels default · 1 source · 1 quote
AITER backend used · 1 source · 1 quote
Container-baked precompiled artifacts used · 1 source · 1 quote
FLASHMLA_SPARSE used · 1 source · 1 quote
FlashQLA used · 1 source · 1 quote
Marlin MoE backend used · 1 source · 1 quote
MiniTriton used · 1 source · 1 quote
MiniTriton 5 used · 1 source · 1 quote
MiniTriton dual-mode tensor library used · 1 source · 1 quote
CUTEDSL optional · 1 source · 1 quote
CUTLASS optional · 1 source · 1 quote
FlashInfer backend optional · 1 source · 1 quote
flash-moba evaluated · 1 source · 1 quote
Flash-Sparse-Attention evaluated · 1 source · 1 quote
ModelOpt AutoQuantize evaluated · 1 source · 1 quote
Triton mentioned · 1 source · 1 quote

By model

Which of this branch's methods each model's own documents describe, and how strongly. Under each model: its strongest treatment anywhere in the branch.

↑