ngxson/llama.cpp

Pull Requests Commits

ci : separate webui from server (#18072)

CISC committed 330 days ago

Verified d6742125

webui: Improve copy to clipboard with text attachments (#17969)

allozaur committed 330 days ago

Verified 3034836d

webui: Add setting to always show sidebar on Desktop (#17809)

allozaur committed 330 days ago

Verified a20979d4

llama : add support for NVIDIA Nemotron 3 Nano (#18058)

danbev committed 330 days ago

Verified 29953417

Webui: Disable attachment button and model selector button when prompt textbox is disabled. (#17925)

dariusjlukas committed 330 days ago

Verified 40d9c394

convert : move rope_parameters to TextModel class (#18061)

CISC committed 331 days ago

Verified d6a1e18c

ggml-hexagon: mm for mtmd (#17894)

joeldushouyu committed 331 days ago

Verified c45f89d5

model : add KORMo model (#18032)

HelloKS committed 331 days ago

Verified 9d52f17a

kv-cache: Fix state restore fragmented cache (#17982)

ssweens committed 331 days ago

Verified 4529c660

Fix unreadable user markdown colors and truncate long texts in deletion dialogs (#17555)

ServeurpersoCom committed 331 days ago

Verified 0f4f35e7

metal: use shared buffers on eGPU (#17866)

jdemeule committed 331 days ago

Verified 165caaf5

mtmd: refactor audio preprocessing (#17978)

ngxson committed 331 days ago

Verified 96a181a9

cli: fixed dead links to tools/main for cli and completion, fixed code owners (#17993)

andrew-aladev committed 331 days ago

Verified 4a4f7e65

webui: add "delete all conversations" button to import/export tab (#17444)

thomasjfox committed 331 days ago

Verified e73d5486

llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)

JohannesGaessler committed 331 days ago

Verified b1f3a6e5

[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4, swiglu_oai (#17826)

NeoZhangJianyu committed 331 days ago

Verified 4aced7a6

model : add glm-asr support (#17901)

piDack committed 331 days ago

Verified 745fa0e7

preset: handle negated arg, reverse the meaning if needed (#18041)

ngxson committed 332 days ago

Verified 52392291

convert : refactor rope scaling handling (#18013)

CISC committed 332 days ago

Verified 5c8a7171

mtmd: enhance image resizing in llava_uhd (#18014)

bluebread committed 332 days ago

Verified 37f5a109

vulkan: fix mul_mat_vec_iq1_s formatting (#18026)

0cc4m committed 332 days ago

Verified 9e6649ec

graph: add f_attn_temp_offset (#18025)

ngxson committed 332 days ago

Verified 0759b09c

common : refactor common_sampler + grammar logic changes (#17937)

ggerganov committed 332 days ago

Verified 254098a2

vulkan: Fix data race/hang in scalar/cm1 flash attention (#17887)

jeffbolznv committed 332 days ago

Verified 3238b140

vulkan: improve mul_mat_vec_iq1_s speed (#17874)

lovedheart committed 332 days ago

Verified 47226716

vulkan: faster q6_k matmul (#17813)

netrunnereve committed 332 days ago

Verified d15d177f

model-conversion : cast logits to float32 (#18009)

ggerganov committed 332 days ago

Verified 77ad8542

models : fix YaRN regression + consolidate logic (#18006)

ggerganov committed 332 days ago

Verified 609a2d02

ggml : arm repack fix build

ggerganov committed 332 days ago

a63cbafb

ggerganov committed 332 days ago

0e592249

Newer Older