ggml-org/llama.cpp

Pull Requests Commits

llama: move moe-cache code out of llama-graph

am17an committed 25 minutes ago

ec6078bf

hexagon: add Q5_0 and Q5_1 support (#32094)

aparmp-quic committed 2 hours ago

Verified 2a4daf0e

server : cancel MCP tool calls on client disconnect or timeout (#32025)

hmblair committed 2 hours ago

Verified d8c8cc4d

qwen3.5: merge tensors on convert also (#32102)

ORippler committed 4 hours ago

Verified 3ba1ce0e

Title: CUDA: few-row MMQ for BS 2-24 (#31533)

anujj committed 5 hours ago

Verified 0fb8f157

ci : build ui on non-slim runner (#32138)

CISC committed 7 hours ago

Verified 827466b9

server: fix SSRF for CORS proxy and media URLs (#32115)

ngxson committed 7 hours ago

Verified 8954f194

server: explicit opt-in tools via non-loopback addr, check cors host port (#32113)

ngxson committed 7 hours ago

Verified a1a68eb7

server: disallow direct access child instance from browser (#32120)

ngxson committed 7 hours ago

Verified e182fdad

server: keep the server awake while a request uses its state (#32133)

ServeurpersoCom committed 7 hours ago

Verified 09452cde

mtmd: require an F32 position embedding for HunyuanVL (#32131)

ServeurpersoCom committed 7 hours ago

Verified cfb9d4b7

mtmd: read the MiniCPM-V projection width from ne[1] (#32132)

ServeurpersoCom committed 7 hours ago

Verified 72f4603c

mtmd: require the MLP projector and patch embedding tensors (#32129)

ServeurpersoCom committed 7 hours ago

Verified 8c388364

mtmd: require a 2x2 spatial merge for the Qwen-VL projectors (#32130)

ServeurpersoCom committed 7 hours ago

Verified 08f49598

ggml : route GATED_DELTA_NET to the SpacemiT RVV kernel (#31897)

gitGurugu committed 8 hours ago

Verified a8575a3e

vulkan : Intel FA kernel for prefill. (#29357)

sliu39 committed 8 hours ago

Verified a963f659

ggml-cpu: use the 4x4 simd_gemm tile on ARM NEON (#32128)

rjtokenring committed 8 hours ago

Verified ab4a77b9

CUDA: Optimize prefil via fuse of w_s scale in epilogue MMQ for nvfp4 checkpoints (#26048)

kmorennv committed 9 hours ago

Verified 0d69255c

ggml-backend : prefetch only inputs computed by earlier splits (#32100)

am17an committed 9 hours ago

Verified 3bce8bd5

ggml : dispatch SpacemiT Q4_1 32x256 through the HP kernel (#31929)

gitGurugu committed 10 hours ago

Verified 81f21f4b

ui: add search_chats tool (#32051)

ngxson committed 10 hours ago

Verified b19f1d9e

ui: install llama-brand from a GitHub tarball instead of git (#32112)

allozaur committed 10 hours ago

Verified d90cfd4a

server: when --tools-runtime is specified, ignore x-tool-runtime (#32119)

ngxson committed 10 hours ago

Verified 60d46a5a

chat : refactor gemma4 to build loose schema rules and clean up (#31915)

aldehir committed 11 hours ago

Verified 93cf736a

llama : avoid touching unused graph metadata pages (#32043)

joelagnel committed 11 hours ago

Verified 4fffab62

sycl: make oneDNN FA cache thread-safe and memoize runtime failures (#31138)

Titaniumtown committed 12 hours ago

Verified 09338b85

sycl : fix AOT for more than 4GB (#31873)

arthw committed 12 hours ago

Verified dcbff216

sycl : use cached device-id in set_main_device (#32013)

zhaoyshine committed 12 hours ago

Verified f3d7725a

CUDA: add cuda debug buffer pool (#31919)

JoeyPatricio committed 12 hours ago

Verified 7021f7e0

opencl: add bin kernel `kernel_gemm_noshuffle_q4_0_f32_32b_trans_ila_a7_bin` (#30947)

shaofeiqi committed 13 hours ago

Verified e0949d09

Older