ggml : update softmax n_task calculation (llama/5126)
3a3eb8e
unverified
snadampal
commited on
Spaces:
Running
Running
Commit History
minor : clean-up some warnings and style (llama/5094)
7df090b
unverified
ggml : parallelize FP32 conversion when using BLAS (llama/5045)
7bf2c87
unverified
llava : MobileVLM support (llama/4954)
dc8f956
unverified
ggml : check ggml_add src1 type (ggml/708)
aa5d6ed
unverified
Judd
Judd
commited on
ggml : add IQ2 to test-backend-ops + refactoring (llama/4990)
227f2ae
unverified
imatrix : offload to GPU support (llama/4957)
6490f98
unverified
ggml : importance matrix support for legacy quants (llama/4969)
d8bb9d8
unverified
ggml : introduce GGML_CALL function annotation (llama/4850)
7815f68
unverified
Add ability to use importance matrix for all k-quants (llama/4930)
7032309
unverified
2-bit quantizations (llama/4897)
8a399ab
unverified
ggml: cache sin/cos for RoPE (llama/4908)
c315fbf
unverified
gguf : fix potential infinite for-loop (llama/4600)
0e93179
unverified
texmex76
Bernhard Gstrein
commited on
llama : ggml-backend integration (llama/4766)
362430b
unverified
ggml : SOTA 2-bit quants (add IQ2_XS) (llama/4856)
5e827d5
unverified
ggml : remove ggml_cpy_inplace and ggml_cont_inplace (ggml/693)
6469bfe
unverified
Timothy Cronin
commited on
Fix execlp call (ggml/689)
abda16e
unverified
Halalaluyafail3
commited on
SOTA 2-bit quants (llama/4773)
75de5bf
unverified
ggml : do not sched_yield when calling BLAS (llama/4761)
5d1dffc
unverified
ggml : extend ggml_get_rows, ggml_repeat, ggml_concat (ggml/639)
f17d170
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
sync : ggml (Metal fixes, new ops, tests) (#1633)
a0d4b48
unverified
sync : ggml (new ops, new backend, etc) (#1602)
895e87a
unverified
ggml : re-enable blas for src0 != F32 (#1583)
87987de
unverified
sync : ggml (ggml-alloc + linker + gguf fixes) (#1501)
58507b9
unverified
whisper : add full CUDA and Metal offloading (#1472)
da4acca
unverified
ggml : fix MIN / MAX macro re-definition
1344fc4
unverified
sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)
7006035
unverified
sync : ggml (const correctness)
4ce2d25
unverified
metal : add F32 support + update bench output
02d7878
unverified
whisper : Metal and ggml-alloc support (#1270)
714ee6b
unverified
whisper : fix bench regression + fix performance when using CPU BLAS (#1275)
abbf5f2
unverified
sync : ggml (HBM + Metal + style) (#1264)
88deeba
unverified
build : do not use _GNU_SOURCE gratuitously (#1129)
beefa34
unverified
Przemysław Pawełczyk
commited on
ggml : posixify pagesize (#1251)
4902c26
unverified
Przemysław Pawełczyk
commited on
ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247)
8bb66c1
unverified
ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220)
d41ba35
unverified
ggml : fix compilation errors incurred by -Werror (#1227)
45ef7b5
unverified
ChangSeok Oh
commited on
ggml : fix compiling when SSE3 is available but not SSSE3 (#1210)
b7995b7
unverified
Przemysław Pawełczyk
commited on
ggml : detect SSSE3 (#1211)
82a619c
unverified
Przemysław Pawełczyk
commited on
ci : more platforms coverage (#1101)
c4448fa
unverified
alonfaraj
Alon Faraj
commited on
Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)"
1e5ddb0
unverified
ggml : sync latest repo (mostly refactoring changes)
d97fd69
unverified
ggml : do not use _GNU_SOURCE gratuitously (#1027)
3a69cdf
unverified
Przemysław Pawełczyk
commited on