GitHub Release: ollama/ollama v0.33.3-rc0 (02.09.2026)

• llama.cpp: version bump b10729

Regenerate the compat hooks patch for b10729: upstream removed the

whole-tensor load_data_for read (last consumer was llama-quantize,

which now reads slabs via load_data_range). Keep the existing hook

surface (constructor, skip loops, load_all_data, mtmd/clip) unchanged

and add maybe_load_text_tensor_range, which materializes a text load

op's output once per tensor and serves the new (offset, size) slab

reads from that cache.

• address comments