ngxson/llama.cpp

Pull Requests Commits
ci : use CUDA label for cuda backend (#24594)
CISC committed 150 days ago
Verified 46722116
add sycl to check-release (#24583)
CISC committed 150 days ago
Verified c2ba3e47
ui : fix llama-ui-embed crash when no asset dir is given (#24597)
aldehir committed 150 days ago
Verified 53bd47ea
Add arch support for cohere2-MoE (#24260)
michaelw9999 committed 150 days ago
Verified 4988f6e8
jinja : fix negative step slice with start/stop values (#24580)
CISC committed 151 days ago
Verified f05cf467
ui: build-time gzip compression (#24571)
ngxson committed 151 days ago
Verified e8067a8b
jinja : fix split and replace with empty first arg (#24574)
CISC committed 151 days ago
Verified 341babcf
vulkan: support non-contig unary/glu ops (#24215)
jeffbolznv committed 151 days ago
Verified 1a7718b4
ui: keep original file name and path (#24568)
ngxson committed 151 days ago
Verified 597b6672
server: clean up static assets handling (#24550)
ngxson committed 151 days ago
Verified 57fe1f07
fit : wrap llama_device_memory_data (#24522)
ggerganov committed 151 days ago
Verified d8a24cce
fix sycl links in release notes (#24527)
muhammad-salem committed 151 days ago
Verified c34b9223
mtmd: add batching API (#24384)
ngxson committed 151 days ago
Verified e37abd6b
ci : unbreak release harder (#24545)
CISC committed 151 days ago
Verified f58bad41
ci : unbreak release (#24544)
CISC committed 151 days ago
Verified cd504466
server : fix reasoning budget WebUI precedence over model.ini (#24517)
ggerganov committed 152 days ago
Verified ebc10770
vulkan: add pipeline barriers for memcpy read operations (#23770)
0cc4m committed 152 days ago
Verified 3e7bd4f3
ui: PWA support (#23871)
allozaur committed 152 days ago
Verified f7ca93d1
fit : avoid including llama-ext.h in fit.h (#24506)
ggerganov committed 152 days ago
Verified 02182fc5
sync : ggml
ggerganov committed 152 days ago
f532be8f
ggml : bump version to 0.15.1 (ggml/1541)
ggerganov committed 152 days ago
e08c226a
vendor : update cpp-httplib to 0.47.0 (#24395)
angt committed 152 days ago
Verified 70b54e14
UI/jpeg exif orientation (#24196)
ServeurpersoCom committed 152 days ago
Verified 6471e3c0
spec: add EAGLE3 speculative decoding support (#18039)
ruixiang63 committed 152 days ago
Verified 88a39274
ggml: support concat for scalar types at cuda backend (#24011)
zihaomu committed 152 days ago
Verified 85f99dca
[SYCL] Fix CI build & release for SYCL backend (#24387)
arthw committed 152 days ago
Verified 099ea76f
opencl: add q5_0/q5_1 gemm and gemv kernels for Adreno (#24319)
shaofeiqi committed 152 days ago
Verified ba1df050
docker : support specifying the GCC version for CUDA (#24447)
wencan committed 152 days ago
Verified 1593d568
vulkan: ifdef eMesaHoneykrisp (build fix) (#24479)
jeffbolznv committed 152 days ago
Verified 4c659550
sync : ggml
ggerganov committed 153 days ago
263cc04a
Terms Of Use Privacy Policy Refund Policy Impressum