Morph MORPH
SIGN IN SIGN UP
dhruvhead / onnxruntime UNCLAIMED
0 0 114 C++

ACTIVITY

Commits Reviews
week month year
COMMITS
20
in the last week
CONTRIBUTORS
9
active
STARS
0
total
FORKS
0
total
TOP CONTRIBUTORS
C
Copilot
6 commits
D
dependabot[bot]
3 commits
T
Tianlei Wu
3 commits
D
danielsongmicrosoft
2 commits
D
David Fan
2 commits
T
TANGBUDU
1 commit
A
aciddelgado
1 commit
K
kunal-vaishnavi
1 commit
M
Mustapha Jaber
1 commit
RECENT COMMITS
D
Bump esbuild and vite in /js/web/test/e2e (#33012)
dependabot[bot]
999e887
D
Bump github/codeql-action/upload-sarif from 3.37.7 to 4.38.2 (#33025)
dependabot[bot]
f05448f
D
Reject recursive function graph attributes (#32864)
danielsongmicrosoft
27f3d47
D
Validate inline raw initializer size before unpacking (#32866)
danielsongmicrosoft
5f052c7
T
[CPU] Support independent scale and output types in DequantizeLinear (#32728)
TANGBUDU
43e2046
T
[CUDA] Fix QMoE MXFP4 W4A16 on SM120/SM121 and speed up FP4 decode (#33067)
Tianlei Wu
3886abd
A
[WebGPU] Add per-head Q/K normalization to PagedAttention (#32808)
aciddelgado
c971ca2
D
[CUDA] Enable SM80+ FP16/BF16 mixed INT2/INT4 QMoE prefill by default (#33005)
David Fan
2cdff3c
C
Run targeted MLAS tests across CPU architectures (#33054)
Copilot
e1b8996
C
[CUDA] Add SparsePagedAttention (#32524)
Copilot
d32356b
T
[CUDA] Avoid repacking NVFP4 QMoE decode weights (#32325)
Tianlei Wu
f084344
T
[CUDA] Fix Protobuf warning in CUDA 13.3 plugin build (#32854)
Tianlei Wu
7da5555
C
[CUDA] Implement SparseAttentionIndexer operator (#32526)
Copilot
5bbba22
C
Add Qwen4-Exp support to VarlenNGramHashMapping (#32467)
Copilot
38c3db5
D
[CUDA] Follow up INT2 grouped GEMM test coverage and plugin build (PR4a2) (#33045)
David Fan
78c8349
K
Fix packed GatedDeltaNet shape inference (#32708)
kunal-vaishnavi
12e7b2b
C
Add weightless hyper-connection fusion operators (#32687)
Copilot
7001d9a
D
Bump actions/setup-java from 5.7.0 to 6.0.1 (#33028)
dependabot[bot]
e368af0
M
Handle optimizer size overflow without exceptions (#32875)
Mustapha Jaber
52e8078
C
[CUDA] Add DynamicSparseAttention (#32525)
Copilot
03ef37f