Skip to content

Actions: gaugarg-nv/llama.cpp

Actions

Python Type-Check

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-type-check.yml
50 workflow runs
50 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
More test fixes Python Type-Check #53: Commit 762a06e pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Fix tests on Vulkan Python Type-Check #52: Commit 466696c pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Fix tests for spec decoding Python Type-Check #51: Commit 3de0910 pushed by gaugarg-nv
1d 0h 0m 1s fix-draft-simple
fix-draft-simple
1d 0h 0m 1s
Fix crash with draft-simple Python Type-Check #50: Commit 0ec5b7f pushed by gaugarg-nv
1d 0h 0m 2s fix-draft-simple
fix-draft-simple
1d 0h 0m 2s
Simpify some of the changes Python Type-Check #49: Commit 5897112 pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Match dist between CPU and GPU Python Type-Check #48: Commit 64c1948 pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Match dist between CPU and GPU Python Type-Check #47: Commit f041ddc pushed by gaugarg-nv
1d 0h 0m 1s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 1s
Don't reuse memory for output views. Python Type-Check #46: Commit 0f740b5 pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
More fixes Python Type-Check #45: Commit 0814d2f pushed by gaugarg-nv
1d 0h 0m 1s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 1s
More fixes Python Type-Check #44: Commit 268e4ed pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Add a numeric context parameter declaring the maximum outputs one seq… Python Type-Check #43: Commit 481261b pushed by gaugarg-nv
1d 0h 0m 1s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 1s
Add a numeric context parameter declaring the maximum outputs one seq… Python Type-Check #42: Commit f2a00aa pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Enable backend sampling with token speculation Python Type-Check #41: Commit 3040817 pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Enable backend sampling with token speculation Python Type-Check #40: Commit 31d4207 pushed by gaugarg-nv
1d 0h 0m 2s backend-sampling-multi-output
backend-sampling-multi-output
1d 0h 0m 2s
Python Type-Check Python Type-Check #39: by gaugarg-nv
1d 0h 0m 3s fuse_gated_delta_net_with_copy
fuse_gated_delta_net_with_copy
1d 0h 0m 3s
Enable backend sampling with token speculation Python Type-Check #38: Commit b2ff0f4 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 Type-Check #37: 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 Type-Check #36: 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 Type-Check #35: Commit 55fe676 pushed by gaugarg-nv
1d 0h 0m 2s gdn-changes
gdn-changes
1d 0h 0m 2s
Make ggml_gated_delta_net take only the initial recurrent state (D, 1… Python Type-Check #34: 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 Type-Check #33: Commit 20073ec pushed by gaugarg-nv
1d 0h 0m 2s fuse_gated_delta_net_with_copy
fuse_gated_delta_net_with_copy
1d 0h 0m 2s
Support -fa auto in llama-bench Python Type-Check #32: 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 Type-Check #31: 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 Type-Check #30: Commit 29c1296 pushed by gaugarg-nv
3m 34s reset_meta_caches
reset_meta_caches
3m 34s
Add --spec-draft-backend-sampling argument. Enabled by default. Python Type-Check #29: Commit b0061f7 pushed by gaugarg-nv
3m 45s mtp_backend_sampling
mtp_backend_sampling
3m 45s