wllama v4.0.0 ships: in-browser llama.cpp up to 2.8x faster with WebGPU hybrid
ngxson · x · 2026-11-23
ngxson released wllama v4.0.0, the WebAssembly binding for llama.cpp: up to 2.8x faster prefill and loading, 2.5x faster generation on Chrome (vs v3.13.0, Apple M5 Max), hybrid CPU + WebGPU on Chrome/Firefox enabling bigger models, no 4GB GGUF size cap, LoRA adapters, speculative decoding (MTP/DFlash/Eagle3), video input and full-duplex realtime audio. MIT-licensed, demo available.
Related event: wllama v4.0.0 Boosts In-Browser LLM Inference Up to 2.8x(4 posts)→
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
- wllama author: RPC-linked wasm instances show little performance loss, credits GGML RPC backend — ngxson · 2026-11-23
- layerpool open-sources layer-split fine-tuning across machines with unchanged HF Trainer — Historical_Syrup_461 · 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