Aleksander Grygier 25f3c82768 ui : replace HF bucket download with GH Releases assets ...

Make the source build fallback (priority 3 in scripts/ui-assets.cmake)
download llama-<version>-ui.tar.gz from GH Releases, verified against
the asset digest from the GitHub API (available for all releases,
including existing ones). When the exact version is not found, fall
back to the most recent bNNNN release, resolved via the API (the
releases are marked as prereleases, so /releases/latest does not match
them). GH_TOKEN/GITHUB_TOKEN can be used for authenticated downloads.

Remove LLAMA_UI_HF_BUCKET and the HF_UI_VERSION env var; the UI
version is now always derived from LLAMA_BUILD_NUMBER.

Assisted-by: pi:Kimi-K3

2026-08-26 14:32:51 +02:00

..

batched-bench

cmake : add install() for impl libraries + fix apple builds (#23511)

2026-05-22 11:46:26 +03:00

cli

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

completion

common: migrate the deprecated --mmap/--no-mmap to --load-mode (#26934)

2026-08-15 16:35:53 +08:00

cvector-generator

cmake : introduce semantic versioning (#26839)

2026-08-12 14:15:03 +02:00

export-lora

docs: fix export-lora --lora-scaled syntax [no release] (#24703)

2026-06-18 16:46:17 +02:00

fit-params

fit: also take into account n_streams (#27496)

2026-08-22 16:16:06 +02:00

gguf-split

cmake : introduce semantic versioning (#26839)

2026-08-12 14:15:03 +02:00

imatrix

imatrix.cpp: Move finite check and only check touched experts (#26861)

2026-08-11 11:18:19 -04:00

llama-bench

fit: also take into account n_streams (#27496)

2026-08-22 16:16:06 +02:00

mtmd

mtmd: video: fix moov atom at the end of file (#27596)

2026-08-24 09:59:04 +02:00

perplexity

quant : Optimise memory usage by evicting weights after processing each layer (#22877)

2026-08-18 16:22:32 +02:00

quantize

cmake : introduce semantic versioning (#26839)

2026-08-12 14:15:03 +02:00

results

libs : rename libcommon -> libllama-common (#21936)

2026-04-17 11:11:46 +03:00

rpc

rpc: support apple RDMA as an RPC transport (#26421)

2026-08-25 20:12:15 +03:00

server

server : reject prefilled assistant messages with tool calls (#27626)

2026-08-25 09:35:22 -05:00

tokenize

tokenize : drop --stdin mutual-exclusion check (#25672)

2026-07-15 18:41:51 +02:00

tts

mtmd: add --mmproj-device argument (#23255)

2026-08-20 18:45:37 +02:00

tuning

metal : per-device tuned (Q, NE) for flash-attn vec (#26570)

2026-08-24 19:22:27 +03:00

ui

ui : replace HF bucket download with GH Releases assets

2026-08-26 14:32:51 +02:00

CMakeLists.txt

metal : per-device tuned (Q, NE) for flash-attn vec (#26570)

2026-08-24 19:22:27 +03:00