Skip to content

Actions: gaugarg-nv/llama.cpp

Actions

Python check requirements.txt

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-check-requirements.yml
33 workflow runs
33 workflow runs

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
Simpify some of the changes Python check requirements.txt #36: Commit 5897112 pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Remove redundant CUDA copies after gated_delta_net. Python check requirements.txt #35: Commit 5ccf6d9 pushed by gaugarg-nv
1d 0h 0m 2s fuse_gated_delta_net_with_copy
fuse_gated_delta_net_with_copy
1d 0h 0m 2s
Remove redundant CUDA copies after gated_delta_net. Python check requirements.txt #34: Commit 15cd2c7 pushed by gaugarg-nv
1d 0h 0m 2s fuse_gated_delta_net_with_copy
fuse_gated_delta_net_with_copy
1d 0h 0m 2s
Make GDN changes in all backends. Address review comments. Python check requirements.txt #33: Commit 55fe676 pushed by gaugarg-nv
1d 0h 0m 3s gdn-changes
gdn-changes
1d 0h 0m 3s
Make ggml_gated_delta_net take only the initial recurrent state (D, 1… Python check requirements.txt #32: Commit 375e6f1 pushed by gaugarg-nv
1d 0h 0m 3s gdn-changes
gdn-changes
1d 0h 0m 3s
Remove redundant CUDA copies after gated_delta_net. Python check requirements.txt #31: Commit 20073ec pushed by gaugarg-nv
1d 0h 0m 4s fuse_gated_delta_net_with_copy
fuse_gated_delta_net_with_copy
1d 0h 0m 4s
Support -fa auto in llama-bench Python check requirements.txt #30: Commit e92f67f pushed by gaugarg-nv
1d 0h 0m 2s fa_auto_llama_bench
fa_auto_llama_bench
1d 0h 0m 2s
Add --list-devices-format json for --list-device Python check requirements.txt #29: Commit da2e876 pushed by gaugarg-nv
1d 0h 0m 1s extend_list_device
extend_list_device
1d 0h 0m 1s
Clear tensor-parallel meta backend caches before reusing the buffer Python check requirements.txt #28: Commit 29c1296 pushed by gaugarg-nv
9m 48s reset_meta_caches
reset_meta_caches
9m 48s
Add --spec-draft-backend-sampling argument. Enabled by default. Python check requirements.txt #27: Commit b0061f7 pushed by gaugarg-nv
7m 58s mtp_backend_sampling
mtp_backend_sampling
7m 58s
Move to backend sampling for MTP draft path Python check requirements.txt #26: Commit 4c330e3 pushed by gaugarg-nv
6m 27s mtp_backend_sampling
mtp_backend_sampling
6m 27s
Fix trailing space Python check requirements.txt #25: Commit de63db6 pushed by gaugarg-nv
5m 24s tp_fit_support
tp_fit_support
5m 24s
Enable Auto parameter fitting in split-mode tensor Python check requirements.txt #24: Commit f46c497 pushed by gaugarg-nv
5m 53s tp_fit_support
tp_fit_support
5m 53s
Python check requirements.txt Python check requirements.txt #23: by gaugarg-nv
7m 17s b9037
b9037
7m 17s
Write a readme on Multi-GPU usage in llama.cpp Python check requirements.txt #22: Commit f3f02e1 pushed by gaugarg-nv
8m 15s multi-gpu-read-me
multi-gpu-read-me
8m 15s
Fix recurrent state serialization for partial reads and writes Python check requirements.txt #21: Commit 92f0041 pushed by gaugarg-nv
4m 50s fix_cache_serialization
fix_cache_serialization
4m 50s
Fix delayed AllReduce on Gemma-4 MoE Python check requirements.txt #20: Commit 4ce8fde pushed by gaugarg-nv
5m 26s gemma4_perf
gemma4_perf
5m 26s
cache subgraph splits when cgraph is unchanged Python check requirements.txt #19: Commit 4bfe714 pushed by gaugarg-nv
5m 15s tp_cpu_overhead
tp_cpu_overhead
5m 15s
Change CMake to use NCCL on Windows Python check requirements.txt #18: Commit 68fb0ba pushed by gaugarg-nv
5m 59s nccl_windows
nccl_windows
5m 59s
Change CMake to use NCCL on Windows Python check requirements.txt #17: Commit a92f245 pushed by gaugarg-nv
4m 46s nccl_windows
nccl_windows
4m 46s
Use the new kernel only for nblocks_stream_k_raw > 4 * ntiles_dst to … Python check requirements.txt #16: Commit 25ef2df pushed by gaugarg-nv
6m 8s fa_opt
fa_opt
6m 8s
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
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 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. Python check requirements.txt #12: Commit 7cfb67e pushed by gaugarg-nv
5m 2s moe_opt
moe_opt
5m 2s