Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity
3,018 Commits 359 Branches 2,870 Tags 350 MiB
sl/cuda-fattn-par-test
Commit Graph

9 Commits

Author SHA1 Message Date
slaren
1ca802a3e0 parallelize fattn compilation test 2024-05-28 01:19:36 +02:00
Johannes Gäßler
f4003cfba1 fix nwarps > batch size 2024-05-27 19:42:16 +02:00
Johannes Gäßler
3194a01058 fix commented-out kernel variants 2024-05-27 19:42:16 +02:00
Johannes Gäßler
672244a88b CUDA: quantized KV support for FA vec 2024-05-27 19:42:16 +02:00
Johannes Gäßler
cd93a28cb1
CUDA: fix FA out-of-bounds reads (#7479) 2024-05-23 00:31:20 +02:00
Johannes Gäßler
38c03478a3
CUDA: fix FA out-of-bounds writes (#7465) 2024-05-22 17:58:25 +02:00
Johannes Gäßler
133d99c599
CUDA: deduplicate FlashAttention code (#7352) 2024-05-18 12:36:25 +02:00
Johannes Gäßler
0fc1e820a9
CUDA: faster large batch FA without tensor cores (#7314) 2024-05-17 18:54:52 +02:00
Johannes Gäßler
dc685be466
CUDA: add FP32 FlashAttention vector kernel (#7188) 
* CUDA: add FP32 FlashAttention vector kernel

* fixup! CUDA: add FP32 FlashAttention vector kernel

* fixup! fixup! CUDA: add FP32 FlashAttention vector kernel

* fixup! fixup! fixup! CUDA: add FP32 FlashAttention vector kernel
 2024-05-12 19:40:45 +02:00