Skip to content

Actions: gaugarg-nv/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
56 workflow runs
56 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Change CMake to use NCCL on Windows Update Operations Documentation #9: Commit 23e1600 pushed by gaugarg-nv
48s nccl_windows
nccl_windows
48s
Change CMake to use NCCL on Windows Check Pre-Tokenizer Hashes #12: Commit 23e1600 pushed by gaugarg-nv
1m 2s nccl_windows
nccl_windows
1m 2s
Change CMake to use NCCL on Windows Python Type-Check #16: Commit 23e1600 pushed by gaugarg-nv
3m 4s nccl_windows
nccl_windows
3m 4s
Change CMake to use NCCL on Windows Copilot Setup Steps #4: Commit 23e1600 pushed by gaugarg-nv
2m 22s nccl_windows
nccl_windows
2m 22s
Change CMake to use NCCL on Windows Python check requirements.txt #15: Commit 23e1600 pushed by gaugarg-nv
6m 55s nccl_windows
nccl_windows
6m 55s
Write an optimized flash_attn_stream_k_fixup kernel Python Type-Check #15: Commit 99c3df8 pushed by gaugarg-nv
3m 4s fa_opt
fa_opt
3m 4s
Reduce the number of stream-k blocks to reduce the overhead of the fl… Check Pre-Tokenizer Hashes #11: Commit 38a6935 pushed by gaugarg-nv
53s reduce_stream_k_block
reduce_stream_k_block
53s
Reduce the number of stream-k blocks to reduce the overhead of the fl… Python Type-Check #14: Commit 38a6935 pushed by gaugarg-nv
2m 41s reduce_stream_k_block
reduce_stream_k_block
2m 41s
Reduce the number of stream-k blocks to reduce the overhead of the fl… Python check requirements.txt #14: Commit 38a6935 pushed by gaugarg-nv
4m 50s reduce_stream_k_block
reduce_stream_k_block
4m 50s
Cherry-pick changes from @am17an PR https://github.com/ggml-org/llama… Python Type-Check #13: Commit 5d282ad pushed by gaugarg-nv
2m 25s moe_opt
moe_opt
2m 25s
Cherry-pick changes from @am17an PR https://github.com/ggml-org/llama… Check Pre-Tokenizer Hashes #10: Commit 5d282ad pushed by gaugarg-nv
54s moe_opt
moe_opt
54s
Cherry-pick changes from @am17an PR https://github.com/ggml-org/llama… Copilot Setup Steps #3: Commit 5d282ad pushed by gaugarg-nv
1m 55s moe_opt
moe_opt
1m 55s
Cherry-pick changes from @am17an PR https://github.com/ggml-org/llama… Python check requirements.txt #13: Commit 5d282ad pushed by gaugarg-nv
6m 5s moe_opt
moe_opt
6m 5s
Optimize MOE GEMV kernel for BS > 1. Check Pre-Tokenizer Hashes #9: Commit 7cfb67e pushed by gaugarg-nv
1m 19s moe_opt
moe_opt
1m 19s
Optimize MOE GEMV kernel for BS > 1. Update Operations Documentation #8: Commit 7cfb67e pushed by gaugarg-nv
59s moe_opt
moe_opt
59s
Optimize MOE GEMV kernel for BS > 1. Python Type-Check #12: Commit 7cfb67e pushed by gaugarg-nv
3m 25s moe_opt
moe_opt
3m 25s
Optimize MOE GEMV kernel for BS > 1. Python check requirements.txt #12: Commit 7cfb67e pushed by gaugarg-nv
5m 2s moe_opt
moe_opt
5m 2s
Increase per-thread work if the K-dimension is small Copilot Setup Steps #2: Commit cfbbfb2 pushed by gaugarg-nv
1m 56s small_k_optimization
small_k_optimization
1m 56s
Increase per-thread work if the K-dimension is small Update Operations Documentation #7: Commit cfbbfb2 pushed by gaugarg-nv
31s small_k_optimization
small_k_optimization
31s
Increase per-thread work if the K-dimension is small Python Type-Check #11: Commit cfbbfb2 pushed by gaugarg-nv
2m 2s small_k_optimization
small_k_optimization
2m 2s
Increase per-thread work if the K-dimension is small Check Pre-Tokenizer Hashes #8: Commit cfbbfb2 pushed by gaugarg-nv
1m 8s small_k_optimization
small_k_optimization
1m 8s
Increase per-thread work if the K-dimension is small Python check requirements.txt #11: Commit cfbbfb2 pushed by gaugarg-nv
5m 0s small_k_optimization
small_k_optimization
5m 0s
Use a single warp per element instead of a single block per element i… Python check requirements.txt #10: Commit 4f20a44 pushed by gaugarg-nv
6m 26s small_k_optimization
small_k_optimization
6m 26s
Use a single warp per element instead of a single block per element i… Check Pre-Tokenizer Hashes #7: Commit 4f20a44 pushed by gaugarg-nv
54s small_k_optimization
small_k_optimization
54s
Use a single warp per element instead of a single block per element i… Python Type-Check #10: Commit 4f20a44 pushed by gaugarg-nv
2m 19s small_k_optimization
small_k_optimization
2m 19s