Ettore Di Giacinto 21eace40ec feat(llama-cpp): expose split_mode option for multi-GPU placement (#9560) ... Adds split_mode (alias sm) to the llama.cpp backend options allowlist, accepting none|layer|row|tensor. The tensor value targets the experimental backend-agnostic tensor parallelism from ggml-org/llama.cpp#19378 and requires a llama.cpp build that includes that PR, FlashAttention enabled, KV-cache quantization disabled, and a manually set context size. Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>		2026-04-25 14:02:57 +02:00
..
_index.en.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
agents.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
api-discovery.md	feat(api): Allow coding agents to interactively discover how to control and configure LocalAI (#9084)	2026-04-04 15:14:35 +02:00
audio-to-text.md	chore(docs): update transcription endpoint	2026-04-14 14:14:54 +00:00
authentication.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
backend-monitor.md	fix(backend-monitor): accept model as a query parameter (#9411)	2026-04-21 22:06:35 +02:00
backends.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
constrained_grammars.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
distributed-mode.md	fix(distributed): correct VRAM/RAM reporting on NVIDIA unified-memory hosts (#9545)	2026-04-24 22:02:23 +02:00
distributed_inferencing.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
distribution.md	fix(docs): commit distribution.md	2026-04-03 10:14:13 +02:00
embeddings.md	feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480)	2026-04-22 21:55:41 +02:00
face-recognition.md	feat(insightface): add antispoofing (liveness) detection (#9515)	2026-04-23 18:28:15 +02:00
fine-tuning.md	fix(docs): Use notice instead of alert (#9134)	2026-03-25 13:55:48 +01:00
gpt-vision.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
GPU-acceleration.md	feat(rocm): bump to 7.x (#9323)	2026-04-12 08:51:30 +02:00
image-generation.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
mcp.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
mlx-distributed.md	feat(mlx-distributed): add new MLX-distributed backend (#8801)	2026-03-09 17:29:32 +01:00
model-gallery.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
object-detection.md	feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480)	2026-04-22 21:55:41 +02:00
openai-functions.md	docs: document tool calling on vLLM and MLX backends	2026-04-13 16:58:55 +00:00
openai-realtime.md	Remove header from OpenAI Realtime API documentation	2026-04-09 09:00:28 +02:00
p2p.md	feat: Add documentation for undocumented API endpoints (#8852)	2026-03-08 17:59:33 +01:00
quantization.md	fix(docs): Use notice instead of alert (#9134)	2026-03-25 13:55:48 +01:00
reranker.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
runtime-settings.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
sound-generation.md	feat: Add documentation for undocumented API endpoints (#8852)	2026-03-08 17:59:33 +01:00
stores.md	feat(face-recognition): add insightface/onnx backend for 1:1 verify, 1:N identify, embedding, detection, analysis (#9480)	2026-04-22 21:55:41 +02:00
text-generation.md	feat(llama-cpp): expose split_mode option for multi-GPU placement (#9560)	2026-04-25 14:02:57 +02:00
text-to-audio.md	fix(docs): fix broken references to distributed mode	2026-04-03 09:46:06 +02:00
video-generation.md	feat: Add documentation for undocumented API endpoints (#8852)	2026-03-08 17:59:33 +01:00
voice-activity-detection.md	feat: Add documentation for undocumented API endpoints (#8852)	2026-03-08 17:59:33 +01:00
voice-recognition.md	feat: voice recognition (#9500)	2026-04-23 12:07:14 +02:00