Termsslug: mla

MLA

多潜头注意力

Attention mechanism compressing keys and values into a low-dimensional latent to cut KV cache cost.

Curated Intelligence

3 items · Page 1/1
Hacker News AIT2·Open Source
72 pts
Developer Rebuilds DeepSeek V3 in 190 Lines of Pure JAX

A developer released an open-source project that reimplements the DeepSeek V3 architecture from scratch in roughly 190 lines of pure JAX, covering Multi-head Latent Attention, decoupled RoPE, DeepSeekMoE and auxiliary-loss-free load balancing, and pretrains it on a MacBook Air. With no Flax, Equinox or PyTorch dependency and parameters as plain dicts of arrays, the code is readable top to bottom, making it a high-value reference for understanding frontier MoE architectures.

vLLM 官方博客T1·Tools
78 pts
vLLM Introduces Decode Context Parallelism to Break MLA and GQA Memory Bottlenecks for Million-Token Agent Workloads

vLLM introduces Decode Context Parallelism (DCP) to address KV cache memory duplication bottlenecks in GQA and MLA architectures during long-context inference. By optimizing context distribution at the decode stage, DCP significantly enhances concurrency and memory efficiency for agent workloads ranging from 64K to 1M tokens on NVIDIA B200 GPUs.