Skip to content

Actions: gaugarg-nv/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
6 workflow runs
6 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Prefer vector flash decoding kernel for Gemma models Python Type-Check #3: Commit f7d07dd pushed by gaugarg-nv
April 3, 2025 12:53 1m 29s gemma_flash_attention
gemma_flash_attention
April 3, 2025 12:53 1m 29s
Prefer vector flash decoding kernel for Gemma models Python check requirements.txt #3: Commit f7d07dd pushed by gaugarg-nv
April 3, 2025 12:53 3m 8s gemma_flash_attention
gemma_flash_attention
April 3, 2025 12:53 3m 8s
CUDA: Improve flash decoding kernel occupancy for BS=1 case Python Type-Check #2: Commit aa5aa01 pushed by gaugarg-nv
March 19, 2025 11:38 1m 13s flash_decoding_improvement
flash_decoding_improvement
March 19, 2025 11:38 1m 13s
CUDA: Improve flash decoding kernel occupancy for BS=1 case Python check requirements.txt #2: Commit aa5aa01 pushed by gaugarg-nv
March 19, 2025 11:38 3m 10s flash_decoding_improvement
flash_decoding_improvement
March 19, 2025 11:38 3m 10s
Enable CUDA Graph on CTK < 12.x Python Type-Check #1: Commit fc7f195 pushed by gaugarg-nv
March 14, 2025 15:28 1m 14s enable_cuda_graph_on_11.x
enable_cuda_graph_on_11.x
March 14, 2025 15:28 1m 14s
Enable CUDA Graph on CTK < 12.x Python check requirements.txt #1: Commit fc7f195 pushed by gaugarg-nv
March 14, 2025 15:28 2m 44s enable_cuda_graph_on_11.x
enable_cuda_graph_on_11.x
March 14, 2025 15:28 2m 44s