Skip to content

Actions: ORippler/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,094 workflow runs
2,094 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Remove unnecessary include from top-k.cu Python Type-Check #11: Commit 90c162a pushed by ORippler
2m 17s osimons/cuda_iterator_in_argsort
osimons/cuda_iterator_in_argsort
2m 17s
Remove unnecessary include from top-k.cu Update Operations Documentation #8: Commit 90c162a pushed by ORippler
13s osimons/cuda_iterator_in_argsort
osimons/cuda_iterator_in_argsort
13s
Remove unnecessary include from top-k.cu Python check requirements.txt #11: Commit 90c162a pushed by ORippler
3m 30s osimons/cuda_iterator_in_argsort
osimons/cuda_iterator_in_argsort
3m 30s
Remove unnecessary include from top-k.cu Check Pre-Tokenizer Hashes #10: Commit 90c162a pushed by ORippler
29s osimons/cuda_iterator_in_argsort
osimons/cuda_iterator_in_argsort
29s
Remove unnecessary include from top-k.cu Copilot Setup Steps #4: Commit 90c162a pushed by ORippler
1m 51s osimons/cuda_iterator_in_argsort
osimons/cuda_iterator_in_argsort
1m 51s
Use two_stage_warp_reduce also in softmax kernel, move smem out of it Python check requirements.txt #10: Commit 1ebe58d pushed by ORippler
3m 24s osimons/factor_out_two_stage_warp_reductions
osimons/factor_out_two_stage_warp_reductions
3m 24s
Use two_stage_warp_reduce also in softmax kernel, move smem out of it Python Type-Check #10: Commit 1ebe58d pushed by ORippler
1m 54s osimons/factor_out_two_stage_warp_reductions
osimons/factor_out_two_stage_warp_reductions
1m 54s
Use two_stage_warp_reduce also in softmax kernel, move smem out of it Update Operations Documentation #7: Commit 1ebe58d pushed by ORippler
13s osimons/factor_out_two_stage_warp_reductions
osimons/factor_out_two_stage_warp_reductions
13s
Use two_stage_warp_reduce also in softmax kernel, move smem out of it Check Pre-Tokenizer Hashes #9: Commit 1ebe58d pushed by ORippler
30s osimons/factor_out_two_stage_warp_reductions
osimons/factor_out_two_stage_warp_reductions
30s
Log all errors in compare_token_data Check Pre-Tokenizer Hashes #8: Commit da27c9b pushed by ORippler
30s osimons/gpu-sampling-equivalence-checks
osimons/gpu-sampling-equivalence-checks
30s
Log all errors in compare_token_data Python Type-Check #9: Commit da27c9b pushed by ORippler
2m 18s osimons/gpu-sampling-equivalence-checks
osimons/gpu-sampling-equivalence-checks
2m 18s
Log all errors in compare_token_data Python check requirements.txt #9: Commit da27c9b pushed by ORippler
3m 22s osimons/gpu-sampling-equivalence-checks
osimons/gpu-sampling-equivalence-checks
3m 22s
Log all errors in compare_token_data Python check requirements.txt #8: Commit 7ee23c0 pushed by ORippler
3m 35s osimons/gpu-sampling-equivalence-checks
osimons/gpu-sampling-equivalence-checks
3m 35s
Log all errors in compare_token_data Update Operations Documentation #6: Commit 7ee23c0 pushed by ORippler
9s osimons/gpu-sampling-equivalence-checks
osimons/gpu-sampling-equivalence-checks
9s
Log all errors in compare_token_data Check Pre-Tokenizer Hashes #7: Commit 7ee23c0 pushed by ORippler
28s osimons/gpu-sampling-equivalence-checks
osimons/gpu-sampling-equivalence-checks
28s
Log all errors in compare_token_data Python Type-Check #8: Commit 7ee23c0 pushed by ORippler
1m 52s osimons/gpu-sampling-equivalence-checks
osimons/gpu-sampling-equivalence-checks
1m 52s
CUDA: Add top-k implementation Update Operations Documentation #5: Commit f23b306 pushed by ORippler
12s gpu-sampling
gpu-sampling
12s
CUDA: Add top-k implementation Check Pre-Tokenizer Hashes #6: Commit f23b306 pushed by ORippler
33s gpu-sampling
gpu-sampling
33s
CUDA: Add top-k implementation Python check requirements.txt #7: Commit f23b306 pushed by ORippler
3m 10s gpu-sampling
gpu-sampling
3m 10s
CUDA: Add top-k implementation Python Type-Check #7: Commit f23b306 pushed by ORippler
2m 15s gpu-sampling
gpu-sampling
2m 15s
Copilot Setup Steps Copilot Setup Steps #3: Commit 6ed6d2b pushed by ORippler
5m 17s osimons/prefetch_gate_bias_in_fused_mmvq
osimons/prefetch_gate_bias_in_fused_mmvq
5m 17s
Check Pre-Tokenizer Hashes Check Pre-Tokenizer Hashes #5: Commit 6ed6d2b pushed by ORippler
48s osimons/prefetch_gate_bias_in_fused_mmvq
osimons/prefetch_gate_bias_in_fused_mmvq
48s
Python check requirements.txt Python check requirements.txt #6: Commit 6ed6d2b pushed by ORippler
5m 34s osimons/prefetch_gate_bias_in_fused_mmvq
osimons/prefetch_gate_bias_in_fused_mmvq
5m 34s
Python Type-Check Python Type-Check #6: Commit 6ed6d2b pushed by ORippler
2m 19s osimons/prefetch_gate_bias_in_fused_mmvq
osimons/prefetch_gate_bias_in_fused_mmvq
2m 19s
Update Operations Documentation Update Operations Documentation #4: Commit 6ed6d2b pushed by ORippler
15s osimons/prefetch_gate_bias_in_fused_mmvq
osimons/prefetch_gate_bias_in_fused_mmvq
15s
ProTip! You can narrow down the results and go further in time using created:<2025-10-29 or the other filters available.