netdevconf.info 的前十大競爭對手

insujang.github.io

This post explains flash attention 1 2. More references are also useful to understand flash attention as well 3 4 5. Backgrounds # Attention # $$\text{Attention}(Q, K, V)=\text{softmax}(\frac{QK^T}{\sqrt{d^k}})V$$ This equation can be implemented as: class OPTAttention(nn.Module): def forward(...): # hidden states is an input tenor of Attention layer # Calculate Q, K, and V with linear projections to the input # query_states = self.q_proj(hidden_states) # key_states = self.k_proj(hidden_states) # value_states = self.

sysctl-explorer.net

painless access to linux sysctl reference documentation

simplyblock.io

Download whitepapers, watch webinars, and explore case studies from simplyblock on NVMe storage, Kubernetes optimization, and cloud cost reduction.

lwn.net

A longstanding bug in the Linux kernel—quite possibly since the first 2.6 release in 2003 [...]

thegeekinthecorner.wordpress.com

Programming odds and ends -- InfiniBand, RDMA, and low-latency networking for now.

drivenets.com

Hillel Kobrinsky, chief strategy officer and co-founder of DriveNets, joined the podcast with an update on how DriveNets plans to invest its new $262 million Series C round of funding, and how the company's focus on virtualization software is impacting innovation and sales cycles with its service provider customers.