Ettore Di Giacinto e2c15e7f20 fix(vram): bound remote GGUF metadata lengths ...

Upgrade the GGUF parser to reject string and array lengths larger than the remaining remote file before allocating them. This prevents malformed or inconsistent range responses from terminating LocalAI during background gallery warming.

Assisted-by: Codex:GPT-5 [apply_patch] [golangci-lint]

2026-09-20 03:05:35 +00:00

..

cache_persistent_test.go

fix(vram): persist remote probe metadata (#11487)

2026-08-23 08:55:13 +02:00

cache.go

fix(vram): persist remote probe metadata (#11487)

2026-08-23 08:55:13 +02:00

estimate_test.go

feat(gallery): Speed up load times and clean gallery entries (#9211)

2026-05-06 14:51:38 +02:00

estimate.go

feat(gallery): let one gallery entry offer several builds of the same model (#10943)

2026-07-20 18:43:02 +02:00

gguf_reader_test.go

fix(vram): bound remote GGUF metadata lengths

2026-09-20 03:05:35 +00:00

gguf_reader.go

fix(vram): contain malformed GGUF metadata (#11374)

2026-08-06 09:01:56 +02:00

hf_estimate_internal_test.go

fix(vram): report largest GGUF quant instead of whole HF repo for gallery size (#10700) (#10707)

2026-07-07 11:50:27 +00:00

hf_estimate_test.go

feat(gallery): let one gallery entry offer several builds of the same model (#10943)

2026-07-20 18:43:02 +02:00

hf_estimate.go

fix(vram): report largest GGUF quant instead of whole HF repo for gallery size (#10700) (#10707)

2026-07-07 11:50:27 +00:00

types.go

feat(gallery): Speed up load times and clean gallery entries (#9211)

2026-05-06 14:51:38 +02:00

vram_suite_test.go

feat(ui): add model size estimation (#8684)

2026-02-28 23:03:47 +01:00