Prime Intellect released Prime Mega MoE, a backward pass for DeepSeek’s fused Mega MoE kernel. It makes the kernel trainable and speeds Qwen3 MoE training steps by up to 34% in prime-rl.
The post Prime Intellect Releases Prime Mega MoE: Trainable Fused MoE Kernel, 3.11x Faster Forward Pass appeared first on MarkTechPost.
Meta released Muse Spark Open, an 816B-parameter open-weight MoE model with 42B active parameters and a 1M-token context. It leads open models on MCP-Atlas and runs on 2…
Moonshot AI released Kimi K3.1 Pro, a 2.8T-parameter, 104B-active MoE model with 1M-token context. It scores 65.7% on Terminal-Bench 4.0, costs $2/$10 per million…
Linux kernel 7.2 reached end of life and all users are now recommended to upgrade their systems to the latest Linux 7.3 kernel series as soon as possible. The post…
Discussion (0)
No comments yet. Start the conversation!