Skip to content

Actions: qualcomm/llama.cpp

Actions

Python check requirements.txt

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-check-requirements.yml
115 workflow runs
115 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
opencl: add flattened Q4_K mv and general Q4_K mm Python check requirements.txt #65: Commit 58d13e9 pushed by shaofeiqi
7m 8s sq/q4_k-flat
sq/q4_k-flat
7m 8s
hex-mm: remove leftover from rebase conflict Python check requirements.txt #64: Commit b120f77 pushed by max-krasnyansky
6m 31s hexagon-hmx-ext
hexagon-hmx-ext
6m 31s
convert : fix/suppress pyright errors (#20442) Python check requirements.txt #63: Commit 983df14 pushed by lhez
4m 58s master
master
4m 58s
llama : enable chunked fused GDN path (#20340) Python check requirements.txt #62: Commit d28961d pushed by tboinovski1
8m 0s master
master
8m 0s
server: Parse port numbers from MCP server URLs in CORS proxy (#20208) Python check requirements.txt #61: Commit 23fbfcb pushed by tboinovski1
4m 46s master
master
4m 46s
opencl: adjust max number of subgroups Python check requirements.txt #60: Commit 435aad0 pushed by lhez
4m 57s sq/opencl-cumsum-op
sq/opencl-cumsum-op
4m 57s
hex-ssm-conv: add local context and fix various issues (spad indexing… Python check requirements.txt #59: Commit daec768 pushed by max-krasnyansky
5m 47s tb/htp-ssm-conv
tb/htp-ssm-conv
5m 47s
Merge branch 'master' into yardent/hvx-op-coverage-bin-fp16 Python check requirements.txt #58: Commit c716428 pushed by YardenTal44
5m 1s yardent/hvx-op-coverage-bin-fp16
yardent/hvx-op-coverage-bin-fp16
5m 1s
hexagon: add llama-completion runner script Python check requirements.txt #57: Commit 83301b6 pushed by tboinovski1
5m 8s tb/wos-add-script
tb/wos-add-script
5m 8s
docs: Fix intel documentation link (#20040) Python check requirements.txt #56: Commit ecd99d6 pushed by tboinovski1
5m 9s master
master
5m 9s
opencl: fix build for non adreno Python check requirements.txt #55: Commit 8ef5b83 pushed by lhez
6m 32s sq/q4_1_mm_opencl_kernels
sq/q4_1_mm_opencl_kernels
6m 32s
snapdragon: update adb and windows scripts to use ubatch-size 256 Python check requirements.txt #54: Commit ccba173 pushed by max-krasnyansky
5m 0s hexagon-ops-local-ctx
hexagon-ops-local-ctx
5m 0s
opencl: optimize mean and sum_row kernels Python check requirements.txt #53: Commit 598c7aa pushed by lhez
6m 4s sq/opencl-mean-sum_rows-opt
sq/opencl-mean-sum_rows-opt
6m 4s
hexagon: refactor matmul entry point to reduce code duplication Python check requirements.txt #52: Commit b2ab988 pushed by max-krasnyansky
5m 29s hexagon-vecdot-2x2
hexagon-vecdot-2x2
5m 29s
opencl: add basic q4_1 mm Python check requirements.txt #51: Commit 2d02bb0 pushed by lhez
5m 33s lh/q4_1-mv
lh/q4_1-mv
5m 33s
opencl: use h for half literals Python check requirements.txt #50: Commit 57a506f pushed by lhez
5m 59s sq/opencl-expm1-softplus-refactor
sq/opencl-expm1-softplus-refactor
5m 59s
opencl: fix whitespace Python check requirements.txt #49: Commit 5854a6e pushed by lhez
5m 8s lh/q4_k-mv
lh/q4_k-mv
5m 8s
opencl: refactor cumsum Python check requirements.txt #48: Commit dd52e3f pushed by shaofeiqi
5m 35s sq/opencl-cumsum-op
sq/opencl-cumsum-op
5m 35s
remove unused argument Python check requirements.txt #47: Commit 1c8211c pushed by shaofeiqi
5m 35s sq/opencl-cumsum-op
sq/opencl-cumsum-op
5m 35s
opencl: refactor cumsum Python check requirements.txt #46: Commit 888f39a pushed by shaofeiqi
5m 19s sq/opencl-cumsum-op
sq/opencl-cumsum-op
5m 19s
jinja : add missing 'in' test to template engine (#19004) (#19239) Python check requirements.txt #45: Commit 0dfcd3b pushed by max-krasnyansky
15m 3s master
master
15m 3s
opencl: fix unused variables Python check requirements.txt #44: Commit 45b5fec pushed by lhez
4m 57s lh/concat-refactor
lh/concat-refactor
4m 57s
Bump max cmake version (needed for Windows on Snapdragon builds) Python check requirements.txt #43: Commit 9410d34 pushed by max-krasnyansky
4m 47s cmake-ver-update
cmake-ver-update
4m 47s
opencl: enforce subgroup size of 64 for adreno for q8_0 Python check requirements.txt #42: Commit 7ae603e pushed by lhez
4m 12s sq/q8_0_mm_opencl_kernel
sq/q8_0_mm_opencl_kernel
4m 12s
Merge branch 'ggml-org:master' into tb/htp-wos Python check requirements.txt #41: Commit 499ccca pushed by tboinovski1
4m 51s tb/htp-wos
tb/htp-wos
4m 51s