6 results found Sort:

xlite-dev
Awesome-LLM-Inference xlite-dev
275
3.9k
gpl-3.0
122
📚A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism etc.
mla vllm deepseek flash-mla minimax-01 awesome-llm deepseek-r1 deepseek-v3 tensorrt-llm llm-inference flash-attention paged-attention flash-attention-3
Created 2023-08-27
471 commits to main branch, last one 4 days ago
fxmeng
TransMLA fxmeng
21
237
mit
4
TransMLA: Multi-Head Latent Attention Is All You Need
mla deepseek attention
Created 2025-01-02
15 commits to main branch, last one about a month ago
hahnec
plenopticam hahnec
37
217
gpl-3.0
8
Light-field imaging application for plenoptic cameras
mla lens depth field light lytro micro toolbox software plenoptic lightfield refocusing application calibration light-field scheimpflug lytro-images sub-aperture image-processing plenoptic-rendering-engine
Created 2019-03-30
1,555 commits to master branch, last one about a year ago
xlite-dev
ffpa-attn-mma xlite-dev
7
169
gpl-3.0
3
📚FFPA(Split-D): Yet another Faster Flash Attention with O(1) GPU SRAM complexity large headdim, 1.8x~3x↑🎉 faster than SDPA EA.
mla cuda sdpa mlsys deepseek attention flash-mla fused-mla deepseek-r1 deepseek-v3 tensor-cores flash-attention
Created 2024-11-29
247 commits to main branch, last one 28 days ago
shadowpa0327
Palu shadowpa0327
4
99
mit
4
[ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
mla deepseek kv-cache-compression kv-cache-quantization
Created 2024-07-02
42 commits to master branch, last one 2 months ago
Bruce-Lee-LY
decoding_attention Bruce-Lee-LY
3
36
bsd-3-clause
2
Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
gpu gqa llm mha mla mqa cuda nvidia flashmla cuda-core inference flashinfer flash-attention decoding-attention large-language-model multi-head-attention
Created 2024-08-14
2 commits to master branch, last one 20 days ago