ggerganov/llama.cpp

Pull Requests Commits

docs: move per-model TTS to /docs, refer it from other pages

ngxson committed 6 hours ago

6da58f16

model : metal : workaround fusion for LFM3 (#32296)

tdakhran committed 7 hours ago

Verified e574a17b

feat: add Inkling 2 support (text + vision) (#32217)

pwilkin committed 8 hours ago

Verified 5c008e00

common : reject out-of-range grammar_triggers type instead of aborting (#30835) (#31478)

IsNot-10 committed 8 hours ago

Verified 9f26fe11

server : Fix connection reuse after streamed responses (#30492)

arcusbuilds committed 8 hours ago

Verified cf9a9957

hexagon: add TIMESTEP_EMBEDDING HVX kernel (#32228)

pdhinaka committed 9 hours ago

Verified dca216ad

memory : fix non-consecutive position warning for M-RoPE (#32287)

nikwen committed 9 hours ago

Verified f8cc5774

llamafile: introduce more Q0 quant support for s390x (#32203)

taronaeo committed 9 hours ago

Verified acf5d545

llama : allocate the tensor staging buffer from the CPU buffer type (#31438)

ykhrustalev committed 9 hours ago

Verified 3e41ae69

vulkan: Explicitly include SPIRV-Headers (#31416)

richiejp committed 9 hours ago

Verified 3bc612fe

vulkan: optimize prompt processing Flash Attention for RDNA3 and RDNA4 (#31323)

0cc4m committed 9 hours ago

Verified d8f30a5b

cuda : keep columns in registers for cooperative softmax (#28982)

sirohikartik committed 9 hours ago

Verified e9641756

vulkan: optimize matrix multiplication for narrow N (#31990)

jeffbolznv committed 9 hours ago

Verified d20426bb

vulkan: use GPU copies on UMA with uncached memory on Intel (#32024)

0cc4m committed 9 hours ago

Verified 19f31e61

sycl : optimize mtmd image processing (#32109)

NickM-27 committed 9 hours ago

Verified 07037ba1

chat : allow undeclared tool calls in LFM2 tool-call grammar (#32164)

tdakhran committed 9 hours ago

Verified 0cc522e4

docs : add OpenVINO backend to ops matrix (#32259)

tokinasin committed 9 hours ago

Verified f08bca8a

chat : allow tool calls inside reasoning blocks for Ministral-3 (#32271)

kukirin-ui committed 9 hours ago

Verified 3c311796

common : fix infinite recursion in debug build for peg parser dump (#32282)

alexzk1 committed 9 hours ago

Verified 8b4ac249

opencl: fixes for q4_k mv oob access, f16 swiglu_oai, cpy with strided dst, batched group_norm and bf16 sigmoid (#32251)

lhez committed 9 hours ago

Verified 1ae047c9

chat : allow Gemma4 tool call during thought (#32232)

cristianadam committed 9 hours ago

Verified 1c2adc75

Fix ctz64 on 32bit (#32273)

miyanyan committed 13 hours ago

Verified a956a852

hexagon: fix fa no-mask tail (#32243)

jhen0409 committed 13 hours ago

Verified c6c0ec6d

qwen2vl : apply FFN weight scales (#32241)

am17an committed 14 hours ago

Verified d0764c5e

convert : register Granite4VisionForConditionalGeneration for text (#32237)

mrutkows committed 17 hours ago

Verified 3549c274

ggml-backend : start a new split at an incompatible weight in a split without inputs (#31775)

am17an committed 17 hours ago

Verified c56be864

convert : pplx-decider must match qwen3.5 model_type (#32156)

jjbuck committed 17 hours ago

Verified a9a5d216

mtmd: fix video pixel aspect ratio and video rotation (#32267)

ngxson committed 18 hours ago

Verified 9d925e7c

mtmd : allow custom video decoder (#32188)

jhen0409 committed 18 hours ago

Verified e3483e40

jinja : reduce template rendering overhead (#32023)

Neroued committed 19 hours ago

Verified 4f2187e7

Older