ggerganov/llama.cpp

Pull Requests Commits

ui: spin the compaction icon while the summary runs

allozaur committed 7 days ago

e285cfe2

ui: open a compaction summary at the top of the screen

allozaur committed 7 days ago

6f6689fe

ui: expand collapsible bodies with a height transition

allozaur committed 7 days ago

883f7387

ui: follow the bottom, otherwise leave the view alone

allozaur committed 7 days ago

2894120e

ui: hand the compact action to the context gauge

allozaur committed 7 days ago

857354c0

ui: keep the summarized turns quiet while a compaction runs

allozaur committed 7 days ago

3b1e02fd

ui: report compaction progress on the row

allozaur committed 7 days ago

accaf63d

ui: give the compaction row its own summary UI

allozaur committed 7 days ago

584326fc

ui: run every compaction summary through one path

allozaur committed 7 days ago

afe06daa

ui: follow the moved models selector in the compaction model field

ServeurpersoCom committed 7 days ago

815edb76

ui: import the model option helpers from models/utils

ServeurpersoCom committed 7 days ago

6e24c83b

ui: fix the model option helpers import path

ServeurpersoCom committed 7 days ago

e138b827

ui: align the compaction model field with project conventions

ServeurpersoCom committed 7 days ago

f9fc748d

ui: allow a dedicated model for conversation compaction

ServeurpersoCom committed 7 days ago

cddfa890

ServeurpersoCom committed 7 days ago

a8187b8b

ui: pre-fill KV cache and refresh context gauge after compaction

ServeurpersoCom committed 7 days ago

ade61a6d

ui: add conversation compaction

ServeurpersoCom committed 7 days ago

0543f7ba

llama : scale moe down projection per expert token (#30861)

ggerganov committed 7 days ago

Verified 8baabd53

Sycl iq3 crash fix (#30604)

anantshri committed 7 days ago

Verified 493253fe

opencl: fix rope program build error with newer Clang (#30893)

bashbaug committed 7 days ago

Verified 339f3242

server : fix usage.completion_tokens undercount with n > 1 (#29486)

unbug committed 7 days ago

Verified 9a3b91c6

server : add POST /tts endpoint for TTS models (#26603)

ngxson committed 7 days ago

Verified 5c0b49a2

server: add realtime transcription API (#30636)

ngxson committed 7 days ago

Verified 1242be66

refactor : move LFM2 shortconv and FFN blocks into a shared LFM base (#30874)

tdakhran committed 7 days ago

Verified 84e66d03

model : support Nemotron-3(.5)-Embed (#30877)

tokinasin committed 8 days ago

Verified 52ffa027

qwen: reshape output to 2d instead of 3d (#30823)

am17an committed 8 days ago

Verified 839a572a

server: Support logprobs with speculative decoding (#27196)

pnb committed 8 days ago

Verified ead9f320

hexagon: fix VTCM size query on images that need layout out-params (#30655)

tdakhran committed 8 days ago

Verified b684b498

mtmd : lfm2 tiles and layout match transformers (#30261)

ykhrustalev committed 8 days ago

Verified 4a45de4f

model : add H2O-Lightning-4B decision model (#30361)

pseudotensor committed 8 days ago

Verified 7e3eeee0

Older