llama.cpp ships v0.9.0, v1.0.0 coming within weeks

llama.cpp has released v0.9.0 with OCP FP8 E4M3 quantization and NCCL multi-node tensor parallelism, and announced that its first major version v1.0.0 will arrive within weeks.

2026-11-05 ~ 2026-11-05 · 3 related posts

• llama.cpp ships v0.9.0, first major v1.0.0 release weeks away — ggerganov · 2026-11-05
• llama.cpp ships v0.9.0 as ggml team gears up for first major v1.0.0 release — ggerganov · 2026-11-05

1 near-duplicate retellings: victormustar