Tag: tensor-parallel

All the articles with the tag "tensor-parallel".

• 18.7× in two days: what sparkinfer-k3 taught me about shipping fast on Gittensor

  6 Aug, 2026

  sparkinfer-k3 took Kimi K3 (2.8T) from 1 tok/s to 3× llama.cpp on 8× H200 in days. The climb, its bugs, and what it taught me about racing on Gittensor's SN74.

• Developing a custom Qwen2.5 72B inference engine from scratch — what is the real bottleneck?

  11 Jun, 2026

  Custom Qwen2.5-72B engine on 8×H200: the real bottleneck isn't the 72B matmuls — it's the 160 all-reduce barriers per token. H200 roofline math, barrier vs. bandwidth anatomy, and why the engine anti-scales at TP=8.