Aleksander Grygier 89c4ba08b2 ui : route chat through the active provider ...

Chat goes through protocol adapters, so an OpenAI-compatible endpoint
speaks its own wire format: per-backend paths and headers, the model on
the request, tools kept on the local server, and token counts synthesized
for endpoints that do not stream their own timings. The server store keeps
the local server's props while another provider is active, a conversation
resolves the provider its model belongs to before sending, and the chat
screen never blocks on the local probe when the install has none.

Assisted-by: pi:llama.cpp/DeepSeek-V4.1-Flash

2026-09-28 17:12:26 +02:00

..

batched-bench

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

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

cli

args: add env vars for temperature, top-p, min-p and penalties (#27380)

2026-09-21 12:47:38 +02:00

completion

args: add env vars for temperature, top-p, min-p and penalties (#27380)

2026-09-21 12:47:38 +02:00

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

llama-bench : fix OOB access of hf_file (#29515)

2026-09-27 10:24:54 +02:00

mtmd

Enables Windows ARM64 build with MSVC cl.exe (#28362)

2026-09-28 10:07:27 +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

common,rpc : simplify fs_create_directory_with_parents() (#29432)

2026-09-25 20:33:37 +02:00

server

server : allow RANK pooling batch splitting for causal LLM rerankers (ie. Qwen3 and Qwen3-VL) (#28876)

2026-09-27 23:28:10 +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 : key the fa-vec tuned table by family instead of SKU (#29075)

2026-09-23 19:23:15 +08:00

ui

ui : route chat through the active provider

2026-09-28 17:12:26 +02:00

CMakeLists.txt

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

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