Default Branch

3ac3c20c96 · ggml-webgpu: Add clang-format job (#24308) · Updated 2026-06-09 05:54:24 +02:00

Branches

102cd98074 · ggml : Q4_3c using 2x "Full range" approach · Updated 2023-04-23 13:56:44 +02:00    wylab

9152
8

71e6ae3779 · ggml : continue from #729 (wip) · Updated 2023-04-22 17:49:07 +02:00    wylab

9152
7

a0242a833c · Minor, plus rebase on master · Updated 2023-04-22 16:07:10 +02:00    wylab

9152
2

4b8d5e3890 · llama : quantize attention results · Updated 2023-04-22 10:35:13 +02:00    wylab

9157
1

1506737499 · Add mmap pages stats (disabled by default) · Updated 2023-04-16 18:22:30 +02:00    wylab

9207
1

36ddd12924 · llama : add flash attention (demo) · Updated 2023-04-05 21:12:04 +02:00    wylab

9273
1

c9c820ff36 · Added support for _POSIX_MAPPED_FILES if defined in source (#564) · Updated 2023-03-28 23:26:25 +02:00    wylab

9507
8

4aeee216fd · Regroup q4_1 dot addition for better numerics. · Updated 2023-03-24 21:20:57 +01:00    wylab

9388
2

66ea164e1d · Kahan summation on Q4_1 · Updated 2023-03-23 04:28:51 +01:00    wylab

9415
2

711224708d · Break up loop for numeric stability · Updated 2023-03-23 03:14:44 +01:00    wylab

9415
2

3a0dcb3920 · Implement server mode. · Updated 2023-03-22 18:34:19 +01:00    wylab

9416
5
dev

a169bb889c · Gate signal support on being on a unixoid system. (#74) · Updated 2023-03-13 04:08:01 +01:00    wylab

9522
0
Included
0cc4m/cuda-get-memory-device-reset

Deleted by Ghost 2026-06-08 14:56:44 +02:00

xsn/fix_conv1d

Deleted by Ghost 2026-06-08 14:56:44 +02:00