Skip to content

Actions: Nexesenex/croco.cpp

Actions

Benchmark

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
191 workflow runs
191 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

b3062 Benchmark #41: Pull request #141 opened by Nexesenex
June 1, 2024 13:41 51m 55s
June 1, 2024 13:41 51m 55s
b3052 Benchmark #40: Pull request #140 opened by Nexesenex
May 30, 2024 23:44 1d 13h 54m 53s
May 30, 2024 23:44 1d 13h 54m 53s
b3028 Benchmark #39: Pull request #139 opened by Nexesenex
May 28, 2024 20:57 1d 17h 9m 14s
May 28, 2024 20:57 1d 17h 9m 14s
b3024 Benchmark #38: Pull request #138 opened by Nexesenex
May 28, 2024 17:06 3h 51m 15s
May 28, 2024 17:06 3h 51m 15s
CUDA: quantized KV support for FA vec Benchmark #37: Pull request #137 opened by Nexesenex
May 25, 2024 19:26 1d 11h 55m 38s
May 25, 2024 19:26 1d 11h 55m 38s
b2998 Benchmark #36: Pull request #136 opened by Nexesenex
May 25, 2024 13:32 1d 1h 8m 30s
May 25, 2024 13:32 1d 1h 8m 30s
Add support for ArcticForCausalLM (#7020) Benchmark #35: Pull request #135 opened by Nexesenex
May 24, 2024 12:57 1d 1h 43m 13s
May 24, 2024 12:57 1d 1h 43m 13s
b2985 Benchmark #34: Pull request #134 opened by Nexesenex
May 23, 2024 14:29 22h 27m 45s
May 23, 2024 14:29 22h 27m 45s
b2968 Benchmark #33: Pull request #133 reopened by Nexesenex
May 22, 2024 16:03 22h 25m 59s
May 22, 2024 16:03 22h 25m 59s
b2968 Benchmark #32: Pull request #133 opened by Nexesenex
May 22, 2024 16:03 20s
May 22, 2024 16:03 20s
b2967 Benchmark #31: Pull request #131 opened by Nexesenex
May 22, 2024 14:13 1h 49m 57s
May 22, 2024 14:13 1h 49m 57s
b2956 Benchmark #30: Pull request #130 opened by Nexesenex
May 21, 2024 16:37 21h 36m 22s
May 21, 2024 16:37 21h 36m 22s
0cc4m/vulkan embedding fix Benchmark #29: Pull request #129 opened by Nexesenex
May 18, 2024 16:15 1d 15h 6m 41s
May 18, 2024 16:15 1d 15h 6m 41s
b2928 Benchmark #28: Pull request #128 opened by Nexesenex
May 18, 2024 16:12 1d 15h 9m 15s
May 18, 2024 16:12 1d 15h 9m 15s
CUDA: deduplicate FlashAttention code Benchmark #27: Pull request #127 opened by Nexesenex
May 17, 2024 22:53 1d 8h 27m 49s
May 17, 2024 22:53 1d 8h 27m 49s
ggml: add thread pool Benchmark #26: Pull request #126 opened by Nexesenex
May 17, 2024 22:34 1d 8h 47m 29s
May 17, 2024 22:34 1d 8h 47m 29s
b2915 Benchmark #25: Pull request #125 opened by Nexesenex
May 17, 2024 22:30 17h 41m 56s
May 17, 2024 22:30 17h 41m 56s
sched : support async weight copy Benchmark #24: Pull request #124 opened by Nexesenex
May 16, 2024 18:12 1d 13h 9m 29s
May 16, 2024 18:12 1d 13h 9m 29s
CUDA: faster large batch FA without tensor cores Benchmark #23: Pull request #123 opened by Nexesenex
May 16, 2024 13:23 1d 1h 17m 32s
May 16, 2024 13:23 1d 1h 17m 32s
b2902 Benchmark #22: Pull request #122 opened by Nexesenex
May 16, 2024 13:21 1d 1h 19m 22s
May 16, 2024 13:21 1d 1h 19m 22s
b2894 Benchmark #21: Pull request #121 opened by Nexesenex
May 15, 2024 19:05 18h 15m 37s
May 15, 2024 19:05 18h 15m 37s
ggml llama: align structs for memory optimization on 64-bit platforms: Benchmark #20: Pull request #120 opened by Nexesenex
May 15, 2024 13:32 1d 1h 8m 21s
May 15, 2024 13:32 1d 1h 8m 21s
Avoid unnecessarily disabling CUDA graphs Benchmark #19: Pull request #119 opened by Nexesenex
May 15, 2024 13:27 1d 1h 13m 24s
May 15, 2024 13:27 1d 1h 13m 24s
b2892 Benchmark #18: Pull request #118 opened by Nexesenex
May 15, 2024 13:24 5h 41m 17s
May 15, 2024 13:24 5h 41m 17s
b2849 Benchmark #17: Pull request #117 opened by Nexesenex
May 11, 2024 08:24 1d 6h 16m 1s
May 11, 2024 08:24 1d 6h 16m 1s