Aleksander Grygier cebb6f38cb ui : replace magic strings in hf service and model status store ...

Extract remaining magic values into named constants/enums:
- HF service: reuse PATH_SEPARATOR for the '/' split, new
  HF_SHARED_DRAFT_TOKEN and HF_SIZE_STRING_REGEX constants.
- Model status store: reuse MODEL_ID.QUANTIZATION_SEPARATOR for ':' and
  PATH_SEPARATOR for the sidecar cache key; new CLI_FLAGS entries for
  --model-draft / -md / --mmproj; a new DownloadStopRequest enum replacing
  the 'pause' | 'cancel' string union.
- Reuse the shared PATH_SEPARATOR in download-options.utils.

Assisted-by: llama-ui:Qwen3.8-Flash-Next

2026-09-04 20:07:37 +02:00

..

batched-bench

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

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

cli

common: rename --tensor-read-lazy to --lazy-mode, add -lzm shorthand (#27969)

2026-08-30 09:18:10 +03:00

completion

common: rename --tensor-read-lazy to --lazy-mode, add -lzm shorthand (#27969)

2026-08-30 09:18:10 +03:00

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

common: rename --tensor-read-lazy to --lazy-mode, add -lzm shorthand (#27969)

2026-08-30 09:18:10 +03:00

mtmd

model, mtmd: fix gemma4 vision handling (#28335)

2026-09-04 12:23:27 +02:00

perplexity

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

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

quantize

quantize: cap working memory size to avoid loading big tensors onto RAM (#27795)

2026-08-27 18:31:13 +02:00

results

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

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

rpc

rpc: avoid serializing buffers from other servers (#26500)

2026-08-30 20:26:16 +03:00

server

server : fix deadlock when removing a finished download

2026-09-04 20:07:37 +02:00

tokenize

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

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

tts

args: add --video-* CLI arguments (#24318)

2026-08-27 12:11:12 +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 magic strings in hf service and model status store

2026-09-04 20:07:37 +02:00

CMakeLists.txt

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

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