Bartowski 18443257a3 server: add ctx-per-slot (--kv-unified-per-slot) (#24124) ... * Add ctx-per-slot argument for unifid KV cache * Swap out ctx fractions for ctx pool slots * Formatting cleanup * Remove ctx-pool-slots, make ctx-per-slot an int * refactor it --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>		2026-08-27 22:39:14 +02:00
..
batched-bench
cli	llama: model_loader: add TENSOR_READ_LAZY (#27794)	2026-08-27 15:14:34 +02:00
completion	llama: model_loader: add TENSOR_READ_LAZY (#27794)	2026-08-27 15:14:34 +02:00
cvector-generator	cmake : introduce semantic versioning (#26839)	2026-08-12 14:15:03 +02:00
export-lora
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	llama : add --n-cpu-ffn option (#26622)	2026-08-27 11:26:42 +02:00
mtmd	args: add --video-* CLI arguments (#24318)	2026-08-27 12:11:12 +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
rpc	rpc: support apple RDMA as an RPC transport (#26421)	2026-08-25 20:12:15 +03:00
server	server: add ctx-per-slot (--kv-unified-per-slot) (#24124)	2026-08-27 22:39:14 +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: Improve Chat Form Actions UI/UX (models selector, add panel) (#27746)	2026-08-27 14:47:36 +02:00
CMakeLists.txt	metal : per-device tuned (Q, NE) for flash-attn vec (#26570)	2026-08-24 19:22:27 +03:00