ngxson/llama.cpp

Pull Requests Commits
vulkan: async and event fixes (#20518)
0cc4m committed 28 days ago
Verified 3a5cb629
server : fix ctx checkpoint invalidation (#20671)
ggerganov committed 28 days ago
Verified 8cc2d812
kleidiai : fix MUL_MAT support for batched (3D) inputs (#20620)
jabr committed 28 days ago
Verified 62767060
vulkan: allow graphics queue only through env var (#20599)
0cc4m committed 28 days ago
Verified 740a447f
[SYCL] ehance UPSCALE to support all UT cases (#20637)
arthw committed 28 days ago
Verified b6c83aad
tools/server: support refusal content for Responses API (#20285)
pwilkin committed 28 days ago
Verified 2e4a6edd
model: mistral small 4 support (#20649)
ngxson committed 28 days ago
Verified d34ff7eb
ci : disable AMX jobs (#20654)
ggerganov committed 28 days ago
Verified 45172df4
benches : add Nemotron 3 Nano on DGX Spark (#20652)
ggerganov committed 28 days ago
Verified 9b342d0a
tests : write to binary buffer to avoid newline translation in jinja -py [no ci] (#20365)
CISC committed 28 days ago
Verified 55e87026
kleidiai: add data type check to get_tensor_traits (#20639)
martin-klacer-arm committed 28 days ago
Verified cf21cdf3
ci : update labeler (#20629)
CISC committed 28 days ago
Verified 0ed99297
jinja : add capability check for object args (#20612)
aldehir committed 28 days ago
Verified 1bbec6a7
sync : ggml
ggerganov committed 28 days ago
f47a246a
ggml : try fix arm build (whisper/0)
ggerganov committed 28 days ago
c0ccbd1f
ggml : extend im2col f16 (ggml/1434)
David366AI committed 28 days ago
f6da02c3
webui: add model information dialog to router mode (#20600)
ServeurpersoCom committed 29 days ago
Verified dddca026
llama-graph: replace cont with reshape for alpha in qwen35 (#20640)
am17an committed 29 days ago
Verified 3c8521c4
webui: Add MCP CORS Proxy detection logic & UI (#20167)
allozaur committed 29 days ago
Verified 67a2209f
Fix model selector locked to first loaded model with multiple models (#20580)
ServeurpersoCom committed 29 days ago
Verified d65c4f2d
webui: use date in more human readable exported filename (#19939)
woof-dog committed 29 days ago
Verified d8c331c0
vulkan: fix flash attention dot product precision (#20589)
0cc4m committed 29 days ago
Verified 46dba9fc
model : wire up Nemotron-H tensors for NVFP4 support (#20561)
CISC committed 29 days ago
Verified de8f01c2
convert : support mixed-precision ModelOpt models with per-tensor NVFP4/FP8 quantization (#20539)
richarddd committed 29 days ago
Verified 079e5a45
common : fix iterator::end() dereference (#20445)
rillomas committed 29 days ago
Verified d3936498
CUDA: GDN hide memory latency (#20537)
am17an committed 29 days ago
Verified 34818ea6
tools/cli: fix disable reasoning (#20606)
pwilkin committed 29 days ago
Verified 9e2e2198
server : fix wait in test_cancel_requests() test (#20601)
ggerganov committed 29 days ago
Verified 88915cb5
sycl : fix for untransposed GDA recurrent state (#20583)
CISC committed 29 days ago
Verified ebbf544e
ci : only save openvino caches on github-hosted master (#20593)
CISC committed 29 days ago
Verified b91d7dfe
Terms Of Use Privacy Policy Refund Policy Impressum