Skip to content

Actions: AD2605/llama.cpp

Actions

Python check requirements.txt

Actions

Loading...
Loading

Show workflow options

Create status badge

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

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

devops: switch to using ubuntu-22.04-s390x image (#16302) Python check requirements.txt #27: Commit 0124ac9 pushed by AD2605
5m 48s master
master
5m 48s
ci : enable Vulkan workflow on Mac (#16194) Python check requirements.txt #26: Commit 0889589 pushed by AD2605
5m 52s master
master
5m 52s
chat : Seed OSS thinking + tool call support (#15552) Python check requirements.txt #25: Commit 60e5eee pushed by AD2605
8m 34s master
master
8m 34s
disable q8_1 quantization only when dst->ne[1] is 1 Python check requirements.txt #24: Commit 9cbb833 pushed by AD2605
4m 12s atharva/fuse_q8_1_q6_k_gemv
atharva/fuse_q8_1_q6_k_gemv
4m 12s
ggml : prevent integer overflow in gguf tensor size calculation (#14595) Python check requirements.txt #23: Commit 26a48ad pushed by AD2605
3m 11s master
master
3m 11s
Add Conv2d for CPU (#14388) Python check requirements.txt #22: Commit 0a5a3b5 pushed by AD2605
3m 15s master
master
3m 15s
wip: q6_k_q8_1_tiled_gemv Python check requirements.txt #21: Commit 806861f pushed by AD2605
11m 17s atharva/tiled_q6_k_gemv
atharva/tiled_q6_k_gemv
11m 17s
opencl: ref count ggml_backend_opencl_context and refactor profilin… Python check requirements.txt #20: Commit 73e53dc pushed by AD2605
6m 35s master
master
6m 35s
ggml : fix repack work size for mul_mat_id (#14292) Python check requirements.txt #19: Commit d27b3ca pushed by AD2605
3m 43s master
master
3m 43s
ggml-cpu : remove the weak alias trick (#14221) Python check requirements.txt #18: Commit 860a9e4 pushed by AD2605
3m 24s master
master
3m 24s
webui: fix sidebar being covered by main content (#14082) Python check requirements.txt #17: Commit dc0623f pushed by AD2605
3m 41s master
master
3m 41s
convert : fix tensor naming conflict for llama 4 vision (#13836) Python check requirements.txt #16: Commit 26b79b6 pushed by AD2605
3m 46s master
master
3m 46s
Merge remote-tracking branch 'origin/master' into ad/quantize_and_reo… Python check requirements.txt #15: Commit 7903264 pushed by AD2605
3m 13s ad/quantize_and_reorder_q8_1
ad/quantize_and_reorder_q8_1
3m 13s
sampling : make sure samplers return at least 1 token (#13822) Python check requirements.txt #14: Commit f9cd683 pushed by AD2605
3m 48s master
master
3m 48s
llama : allow custom list of swa_layers (#13726) Python check requirements.txt #13: Commit 8a2afb7 pushed by AD2605
3m 3s master
master
3m 3s
mtmd : add vision support for llama 4 (#13282) Python check requirements.txt #12: Commit 92ecdcc pushed by AD2605
3m 14s master
master
3m 14s
CANN: Support MOE Model MUL_MAT_ID (#13042) Python check requirements.txt #11: Commit 33d7aed pushed by AD2605
2m 53s master
master
2m 53s
server : proper error handling for missing elements in messages array… Python check requirements.txt #10: Commit c753d7b pushed by AD2605
2m 54s master
master
2m 54s
sycl: simplify bin_bcast_kernel Python check requirements.txt #9: Commit 6c2091f pushed by AD2605
2m 53s ad/simplify_binbcast
ad/simplify_binbcast
2m 53s
clip : cap max image size 1024 for qwen vl model (#13478) Python check requirements.txt #8: Commit de4c07f pushed by AD2605
3m 2s master
master
3m 2s
server : (webui) fix a very small misalignment (#13387) Python check requirements.txt #7: Commit ee01d71 pushed by AD2605
5m 51s master
master
5m 51s
sycl: simplify bin_bcast_kernel Python check requirements.txt #6: Commit f44f620 pushed by AD2605
3m 25s atharva/optimize_bin_b_cast
atharva/optimize_bin_b_cast
3m 25s
llama : deci : support ffn-free with attention (#13296) Python check requirements.txt #5: Commit bc4e112 pushed by AD2605
2m 50s master
master
2m 50s
clip : fix confused naming ffn_up and ffn_down (#13290) Python check requirements.txt #4: Commit 5215b91 pushed by AD2605
2m 55s master
master
2m 55s
sycl: simplify bin_bcast_kernel Python check requirements.txt #3: Commit 9530d65 pushed by AD2605
4m 45s atharva/optimize_bin_b_cast
atharva/optimize_bin_b_cast
4m 45s