Skip to content

Actions: intel/xFasterTransformer

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
813 workflow runs
813 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

add bf16_int8 support for invokeLayerLLaMA API XFT PR Validation #863: Pull request #470 synchronize by miaojinc
August 26, 2024 02:59 1d 13h 33m 28s miaojinc:main
miaojinc:main
August 26, 2024 02:59 1d 13h 33m 28s
add bf16_int8 support for invokeLayerLLaMA API XFT PR Validation #862: Pull request #470 synchronize by miaojinc
August 15, 2024 08:50 1d 7h 42m 12s miaojinc:main
miaojinc:main
August 15, 2024 08:50 1d 7h 42m 12s
docs: add Japanese README XFT PR Validation #861: Pull request #474 opened by eltociear
August 8, 2024 07:23 1d 5h 21m 30s eltociear:add-japanese-readme
eltociear:add-japanese-readme
August 8, 2024 07:23 1d 5h 21m 30s
[Version] v1.8.1. (#30) XFT PR Validation #16: Commit df57cb2 pushed by Duyi-Wang
July 31, 2024 08:08 1d 8h 24m 49s v1.8.1
v1.8.1
July 31, 2024 08:08 1d 8h 24m 49s
[Version] v1.8.0. (#22) XFT PR Validation #15: Commit faa25f4 pushed by Duyi-Wang
July 23, 2024 01:25 32s v1.8.0
v1.8.0
July 23, 2024 01:25 32s
add bf16_int8 support for invokeLayerLLaMA API XFT PR Validation #860: Pull request #470 opened by miaojinc
July 22, 2024 03:12 22h 12m 52s miaojinc:main
miaojinc:main
July 22, 2024 03:12 22h 12m 52s
[Kernel] Upgrade xDNN to v1.5.2 and make AMX_FP16 work XFT PR Validation #859: Pull request #468 opened by pujiang2018
July 8, 2024 14:18 1d 2h 14m 31s pujiang/feature/amx_fp16
pujiang/feature/amx_fp16
July 8, 2024 14:18 1d 2h 14m 31s
[Kernel] Make SelfAttention prepared for AMX_FP16; More balanced task split in Cross Attention XFT PR Validation #857: Pull request #466 opened by pujiang2018
July 5, 2024 03:51 1d 12h 41m 34s pujiang/feature/amx_fp16
pujiang/feature/amx_fp16
July 5, 2024 03:51 1d 12h 41m 34s
Add env param KV_CACHE_LOCATION to control kv cache memory numanode location XFT PR Validation #855: Pull request #462 synchronize by a3213105
July 3, 2024 10:46 1d 5h 46m 35s a3213105:kvcache_location
a3213105:kvcache_location
July 3, 2024 10:46 1d 5h 46m 35s
[Layers] Fix invokeAttentionLLaMA API XFT PR Validation #854: Pull request #464 opened by wenhuanh
July 3, 2024 08:45 1d 7h 16m 12s wenhuanh:fix/attention-layer
wenhuanh:fix/attention-layer
July 3, 2024 08:45 1d 7h 16m 12s
Add env param KV_CACHE_LOCATION to control kv cache memory numanode location XFT PR Validation #853: Pull request #462 synchronize by a3213105
July 3, 2024 02:46 1d 13h 46m 29s a3213105:kvcache_location
a3213105:kvcache_location
July 3, 2024 02:46 1d 13h 46m 29s
Add env param KV_CACHE_LOCATION to control kv cache memory numanode location XFT PR Validation #852: Pull request #462 synchronize by a3213105
July 2, 2024 13:51 1d 2h 41m 10s a3213105:kvcache_location
a3213105:kvcache_location
July 2, 2024 13:51 1d 2h 41m 10s
[Dependency] Bump web_demo requirement. XFT PR Validation #851: Pull request #463 opened by Duyi-Wang
July 2, 2024 02:33 1d 13h 59m 49s Duyi-Wang:gradio_4.37.1
Duyi-Wang:gradio_4.37.1
July 2, 2024 02:33 1d 13h 59m 49s
[Version] v1.7.3. XFT PR Validation #14: Commit d01f0fd pushed by Duyi-Wang
July 1, 2024 01:52 1d 14h 40m 6s v1.7.3
v1.7.3
July 1, 2024 01:52 1d 14h 40m 6s
Add env param KV_CACHE_LOCATION to control kv cache memory numanode location XFT PR Validation #850: Pull request #462 opened by a3213105
June 28, 2024 04:44 3m 19s a3213105:kvcache_location
a3213105:kvcache_location
June 28, 2024 04:44 3m 19s
[Layers] Enable AMX FP16 of FlashAttn XFT PR Validation #849: Pull request #459 synchronize by abenmao
June 28, 2024 02:25 1h 3m 58s abenmao:layers/flashAttn/amx_fp16
abenmao:layers/flashAttn/amx_fp16
June 28, 2024 02:25 1h 3m 58s
[Layers] Enable AMX FP16 of FlashAttn XFT PR Validation #848: Pull request #459 synchronize by abenmao
June 28, 2024 01:43 3m 26s abenmao:layers/flashAttn/amx_fp16
abenmao:layers/flashAttn/amx_fp16
June 28, 2024 01:43 3m 26s
[Layers] Enable AMX FP16 of FlashAttn XFT PR Validation #847: Pull request #459 synchronize by abenmao
June 27, 2024 06:13 22m 12s abenmao:layers/flashAttn/amx_fp16
abenmao:layers/flashAttn/amx_fp16
June 27, 2024 06:13 22m 12s
[Layers] Enable AMX FP16 of FlashAttn XFT PR Validation #846: Pull request #459 synchronize by abenmao
June 27, 2024 06:01 4m 9s abenmao:layers/flashAttn/amx_fp16
abenmao:layers/flashAttn/amx_fp16
June 27, 2024 06:01 4m 9s
[Kernel] Cache oneDNN primitive when M < XFT_PRIMITIVE_CACHE_M, default 256. XFT PR Validation #845: Pull request #460 synchronize by Duyi-Wang
June 26, 2024 08:42 23m 2s Duyi-Wang:prim_cache
Duyi-Wang:prim_cache
June 26, 2024 08:42 23m 2s
[Layers] Enable AMX FP16 of FlashAttn XFT PR Validation #844: Pull request #459 synchronize by abenmao
June 26, 2024 07:20 22m 26s abenmao:layers/flashAttn/amx_fp16
abenmao:layers/flashAttn/amx_fp16
June 26, 2024 07:20 22m 26s
[Model] Group support for int8/int4 models XFT PR Validation #843: Pull request #461 opened by xiangzez
June 26, 2024 07:01 54s xiangzez:group_support
xiangzez:group_support
June 26, 2024 07:01 54s
[Kernel] Cache oneDNN primitive when M < XFT_PRIMITIVE_CACHE_M, default 256. XFT PR Validation #842: Pull request #460 opened by Duyi-Wang
June 26, 2024 06:03 24m 55s Duyi-Wang:prim_cache
Duyi-Wang:prim_cache
June 26, 2024 06:03 24m 55s
[Layers] Enable AMX FP16 of FlashAttn XFT PR Validation #841: Pull request #459 synchronize by abenmao
June 26, 2024 03:47 23m 21s abenmao:layers/flashAttn/amx_fp16
abenmao:layers/flashAttn/amx_fp16
June 26, 2024 03:47 23m 21s
[Layers] Enable AMX FP16 of FlashAttn XFT PR Validation #840: Pull request #459 opened by abenmao
June 25, 2024 10:22 23m 51s abenmao:layers/flashAttn/amx_fp16
abenmao:layers/flashAttn/amx_fp16
June 25, 2024 10:22 23m 51s