ggml-org/llama.cpp

Pull Requests Commits
llama : use std::abs instead of abs (#16853)
kaetemi committed 216 days ago
Verified d7395115
vulkan: Handle argsort with a large number of rows (#16851)
jeffbolznv committed 216 days ago
Verified 052df28b
Hide latency of bias and gate-loading (#16847)
ORippler committed 216 days ago
Verified 8b11deea
vulkan: Fuse rope+set_rows (#16769)
jeffbolznv committed 216 days ago
Verified b9ce9401
llama: fix ASAN error with M-RoPE (#16848)
ngxson committed 216 days ago
Verified 3464bdac
llama: store mrope data in KV cell (#16825)
ngxson committed 216 days ago
Verified e3af5563
vulkan: Update topk_moe fusion to handle gpt's late softmax (#16656)
jeffbolznv committed 216 days ago
Verified 10fcc412
Vulkan MMQ Integer Dot Refactor and K-Quant support (#16536)
0cc4m committed 216 days ago
Verified bcf5bda6
Hexagon Op queue & dispatch optimizations (#16820)
max-krasnyansky committed 216 days ago
Verified 3eb2be1c
CUDA: use fastdiv in set-rows (#16834)
am17an committed 216 days ago
Verified e41bcce8
vendor : sync minja (#16500)
CISC committed 216 days ago
Verified 144a4ce8
vulkan: Call ggml_vk_buffer_write_2d from ggml_vk_buffer_copy (#16793)
jeffbolznv committed 216 days ago
Verified f549b000
CUDA: Fix bug in topk-moe for gpt-oss (#16821)
am17an committed 216 days ago
Verified 9a3ea685
sycl: add RMS_NORM_BACK operation support (#16808)
YaelLogic committed 217 days ago
Verified 338074c3
cuda: add SET operation support (#16804)
YaelGitAccount committed 217 days ago
Verified 851553ea
memory : remove KV cache size padding (#16812)
ggerganov committed 217 days ago
Verified 85a7d867
llama-bench : clarify benchmarked parts of the computation (#16823)
ggerganov committed 217 days ago
Verified a8ca18b4
initialise buffer.device in ggml_hexagon_session (#16816)
l3utterfly committed 217 days ago
Verified 8284efc3
embedding: add raw option for --embd-output-format (#16541)
SamMalayek committed 217 days ago
Verified 1c1409e1
llama: consistent ctx <-> buf order for KV cache (#16746)
JohannesGaessler committed 217 days ago
Verified 7a0e900e
grammar : support array references in json schema (#16792)
aldehir committed 217 days ago
Verified 280d97be
CANN: Improve device ID handling and aclnnArange checks (#16752)
noemotiovon committed 218 days ago
Verified 3479efd1
CUDA: add unused vars to mmvf and mmvq (#16807)
am17an committed 218 days ago
Verified 463bbf20
sycl: add SSM_CONV operation support (#16800)
tamarPal committed 218 days ago
Verified ad8d36be
chat: Add LFM2 tool handling (#16763)
ykhrustalev committed 218 days ago
Verified c053e18a
mtmd : fix idefics3 preprocessing (#16806)
ngxson committed 218 days ago
Verified e1ab0848
llama : disable pipeline parallelism if compute buffer allocation fails (#16748)
slaren committed 218 days ago
Verified 5a4ff43e
ggml : fix interpolate with align-corners and ne=1 (#16700)
Acly committed 218 days ago
Verified 10640e31
HIP: fix AMDGPU_TARGETS, update documentation (#16803)
JohannesGaessler committed 218 days ago
Verified 80d28f10
model : add LightOnOCR-1B model (#16764)
ngxson committed 218 days ago
Verified c55d53ac
Terms Of Use Privacy Policy Refund Policy Impressum