wllama author: RPC-linked wasm instances show little performance loss, credits GGML RPC backend
ngxson · x · 2026-11-23
Following up on wllama v4.0, author ngxson reports that splitting the wasm runtime into multiple RPC-linked instances works well with very little performance degradation. He credits @rgerganov's work on the GGML RPC backend, calling it an unthinkable-but-effective place to apply that architecture.
More from Infra
- KV cache offload to RAM runs Qwen 3.8 with 8x200k streams on 4x3090 — Mr_Moonsilver · 2026-11-23
- OpenAI chart reveals unreleased GPT-6 Astra models; Domingos questions billions for <0.3 bits — pmddomingos · 2026-11-23
- layerpool open-sources layer-split fine-tuning across machines with unchanged HF Trainer — Historical_Syrup_461 · 2026-11-23
- wllama v4.0.0 ships: in-browser llama.cpp up to 2.8x faster with WebGPU hybrid — ngxson · 2026-11-23
- French dev laments missed chance to build green data center ecosystem on low-carbon grid — Dimillian · 2026-11-23
- Fchollet: deployment friction may be the best thing for AI infra, stretching the buildout timeline — npinto · 2026-11-23