Spaces:
Running
Running
Commit History
extra : update sync scripts
d99e873
unverified
sync : ggml (#0)
fded75b
unverified
sync : ggml
278a9b3
unverified
sync : ggml
5a9540e
unverified
sync : ggml
34bdd70
unverified
sync : ggml
6a472b5
unverified
scripts : sync-ggml-am.sh add option to skip commits
c34dd82
unverified
sync : ggml
18bfc83
unverified
sync : ggml
2ed0a44
unverified
sync : ggml
9af4c11
unverified
fix : cuda order of synchronization when setting a buffer (ggml/679)
e48c553
unverified
Erik Scholz
slaren
commited on
metal : switch back to default.metallib (ggml/681)
b945a8f
unverified
cuda : simplify expression
cda4a91
scripts : fix sync order + metal sed
1785412
scripts : do not sync commits from this repo
397f291
unverified
sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691)
919a447
unverified
sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677)
aa86ade
unverified
bench.py : add different large models (#1655)
282c3a3
unverified
Alfredo Montesinos
commited on
bench-all : add distil models
09d2496
unverified
bench-all : indentations
92df795
unverified
whisper : make large version explicit + fix data size units (#1493)
03a3210
unverified
whisper : add batched decoding (#1486)
0131aa6
unverified
whisper : add full CUDA and Metal offloading (#1472)
da4acca
unverified
whisper : add support for large v3 (#1444)
9908abb
unverified
cuda : fix HIPBLAS build
46033e6
unverified
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)
7006035
unverified
extra: Add benchmark script implemented in Python (#1298)
c587102
unverified
Neil Chudleigh
commited on
metal : add F32 support + update bench output
02d7878
unverified
whisper : Metal and ggml-alloc support (#1270)
714ee6b
unverified
extra : update 'quantize-all.sh' to quantize all downloaded models (#1054)
b2215ea
unverified
thefinaldegree
commited on
metal : sync ggml-metal (ref #1047)
799974c
unverified
opencl : sync latest ggml-opencl
ced3ca3
unverified
extra : update ggml sync script
55ef935
unverified
ggml : sync ggml (clBLAST + tensor names)
f50d3b3
unverified
bench : improve benchmarks
d75ae65
unverified
whisper : add integer quantization support (#540)
a5f8f3c
unverified
extra : add sync-ggml.sh script
a899032
unverified
whisper : add Core ML support (#566)
1fd4bde
unverified
bench-wts.sh : rename script + add execute permission
f0a2b23
unverified
qual-bench.sh : add quality comparison tool, and update main.cpp to allow using a font file (#569)
adb49fb
unverified
venkr
commited on