Skip to content

Actions: huggingface/candle

Actions

CI / cuda

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
ci_cuda.yaml
2,473 workflow run results
2,473 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Metal Unary: Add benchmarks and process kernels in a tile based fashion CI / cuda #2704: Pull request #2056 synchronize by tomsanbear
April 20, 2024 15:02 2s tomsanbear:BenchUnary
tomsanbear:BenchUnary
April 20, 2024 15:02 2s
Use llama v3 by default + add to readme. CI / cuda #2703: Pull request #2094 opened by LaurentMazare
April 20, 2024 12:58 5m 2s readme
readme
April 20, 2024 12:58 5m 2s
Only download the weights in the main process (and not in the child processes). CI / cuda #2702: Pull request #2093 opened by LaurentMazare
April 20, 2024 10:52 5m 0s llama-mp-fix-download
llama-mp-fix-download
April 20, 2024 10:52 5m 0s
Multiprocess/multi-GPU support for llama 3. CI / cuda #2701: Pull request #2092 synchronize by LaurentMazare
April 20, 2024 10:43 4m 9s llama-3-mp
llama-3-mp
April 20, 2024 10:43 4m 9s
Multiprocess/multi-GPU support for llama 3. CI / cuda #2700: Pull request #2092 opened by LaurentMazare
April 20, 2024 10:35 5m 12s llama-3-mp
llama-3-mp
April 20, 2024 10:35 5m 12s
Fix for gemma MQA. CI / cuda #2699: Pull request #2091 opened by LaurentMazare
April 19, 2024 17:43 5m 28s gemma-fix
gemma-fix
April 19, 2024 17:43 5m 28s
Also enable llama-v3 8b instruct. CI / cuda #2698: Pull request #2088 opened by LaurentMazare
April 19, 2024 06:33 15m 54s llama-v3-instruct
llama-v3-instruct
April 19, 2024 06:33 15m 54s
Add support for llama3 on the quantized example CI / cuda #2697: Pull request #2086 synchronize by LaurentMazare
April 18, 2024 20:42 3s tomsanbear:Llama3Support
tomsanbear:Llama3Support
April 18, 2024 20:42 3s
Add support for llama3 on the quantized example CI / cuda #2696: Pull request #2086 synchronize by tomsanbear
April 18, 2024 20:35 2s tomsanbear:Llama3Support
tomsanbear:Llama3Support
April 18, 2024 20:35 2s
Use faster rotary embeddings for llama like models. CI / cuda #2695: Pull request #2087 opened by LaurentMazare
April 18, 2024 20:25 5m 26s faster-rot-emb-llama
faster-rot-emb-llama
April 18, 2024 20:25 5m 26s
Add support for llama3 on the quantized example CI / cuda #2694: Pull request #2086 opened by tomsanbear
April 18, 2024 20:23 2s tomsanbear:Llama3Support
tomsanbear:Llama3Support
April 18, 2024 20:23 2s
Llama v3. CI / cuda #2693: Pull request #2085 synchronize by LaurentMazare
April 18, 2024 20:07 4m 56s llama-v3
llama-v3
April 18, 2024 20:07 4m 56s
Llama v3. CI / cuda #2692: Pull request #2085 synchronize by LaurentMazare
April 18, 2024 20:03 3m 27s llama-v3
llama-v3
April 18, 2024 20:03 3m 27s
Llama v3. CI / cuda #2691: Pull request #2085 opened by LaurentMazare
April 18, 2024 19:44 5m 26s llama-v3
llama-v3
April 18, 2024 19:44 5m 26s
Fix the silu gradient issue on 0. CI / cuda #2689: Pull request #2083 opened by LaurentMazare
April 18, 2024 09:15 5m 17s silu-grad-fix
silu-grad-fix
April 18, 2024 09:15 5m 17s
Minor fix to the readme. CI / cuda #2688: Pull request #2080 opened by LaurentMazare
April 17, 2024 20:42 5m 12s readme-update
readme-update
April 17, 2024 20:42 5m 12s
Prepare for supporting phi-2 properly in the quantized model. CI / cuda #2687: Pull request #2078 synchronize by LaurentMazare
April 17, 2024 08:23 3m 14s phi2-gguf
phi2-gguf
April 17, 2024 08:23 3m 14s
Prepare for supporting phi-2 properly in the quantized model. CI / cuda #2686: Pull request #2078 synchronize by LaurentMazare
April 17, 2024 07:28 3m 2s phi2-gguf
phi2-gguf
April 17, 2024 07:28 3m 2s
Prepare for supporting phi-2 properly in the quantized model. CI / cuda #2685: Pull request #2078 opened by LaurentMazare
April 17, 2024 07:15 5m 6s phi2-gguf
phi2-gguf
April 17, 2024 07:15 5m 6s
Add more QMMV cuda kernels. CI / cuda #2684: Pull request #2077 synchronize by LaurentMazare
April 17, 2024 06:31 4m 28s qmmv8
qmmv8
April 17, 2024 06:31 4m 28s
Add more QMMV cuda kernels. CI / cuda #2683: Pull request #2077 synchronize by LaurentMazare
April 17, 2024 06:23 4m 20s qmmv8
qmmv8
April 17, 2024 06:23 4m 20s
Add more QMMV cuda kernels. CI / cuda #2682: Pull request #2077 opened by LaurentMazare
April 17, 2024 06:06 5m 23s qmmv8
qmmv8
April 17, 2024 06:06 5m 23s
Add the mmv kernels for small batch sizes. CI / cuda #2681: Pull request #2075 synchronize by LaurentMazare
April 16, 2024 19:24 4m 4s more-mmv-kernels
more-mmv-kernels
April 16, 2024 19:24 4m 4s
Add the mmv kernels for small batch sizes. CI / cuda #2680: Pull request #2075 synchronize by LaurentMazare
April 16, 2024 16:50 9m 16s more-mmv-kernels
more-mmv-kernels
April 16, 2024 16:50 9m 16s
Add the mmv kernels for small batch sizes. CI / cuda #2679: Pull request #2075 synchronize by LaurentMazare
April 16, 2024 16:26 4m 9s more-mmv-kernels
more-mmv-kernels
April 16, 2024 16:26 4m 9s