Xuan-Son Nguyen dff15d4ac9 server: (router) add LRU scheduler (#26572) ...

* add lru_sched

* handle coalescing (req leaves waiting queue)

* add tests

* fix stream case

* address review comments

2026-08-07 14:46:53 +02:00

..

batched-bench

…

cli

sampler : remove "full-context windows" from history-based samplers (#26524)

2026-08-04 21:28:55 +03:00

completion

sampler : remove "full-context windows" from history-based samplers (#26524)

2026-08-04 21:28:55 +03:00

cvector-generator

…

export-lora

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

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

fit-params

…

gguf-split

gguf-split: Add option to delete split parts during merge (#26538)

2026-08-04 21:27:47 +03:00

imatrix

Move duplicated imatrix code into single common imatrix-loader.cpp (#22445)

2026-06-04 17:45:40 +02:00

llama-bench

common : add common_print_available_devices() (#26170)

2026-07-27 18:19:59 +02:00

mtmd

mtmd: stop feeding the text stream again during Qwen3-TTS generation (#26706)

2026-08-07 13:32:52 +02:00

parser

chat : enable tool call in thinking for DS4 (#26269)

2026-08-01 00:13:07 -05:00

perplexity

…

quantize

Add Q2_0 quantization: type definition and CPU backend (#24448)

2026-07-07 12:05:47 -07:00

results

…

rpc

binaries : Improve rpc-server and export-graph-ops names. (#25045)

2026-06-27 10:31:29 +03:00

server

server: (router) add LRU scheduler (#26572)

2026-08-07 14:46:53 +02:00

tokenize

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

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

tts

mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254)

2026-08-04 17:26:15 +02:00

ui

ui: read model modalities from the router model list (#26709)

2026-08-07 12:07:58 +02:00

CMakeLists.txt

cmake: skip cvector-generator and export-lora when CPU backend is disabled (#24053)

2026-06-04 13:13:19 +03:00