Skip to content

Actions: PrismML-Eng/llama.cpp

Actions

Update Operations Documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
update-ops-docs.yml
10 workflow runs
10 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
pr2wt : symlink .pi (#22386) Update Operations Documentation #10: Commit f535774 pushed by khosravipasha
28s master
master
28s
metal: Implement ROLL op (#21946) Update Operations Documentation #9: Commit ae2d348 pushed by khosravipasha
35s master
master
35s
Merge branch 'pr-21636' into prism-new Update Operations Documentation #8: Commit 6df15a6 pushed by khosravipasha
31s prism
prism
31s
ggml-webgpu: Add the support of MUL_MAT_ID (#21147) Update Operations Documentation #7: Commit d0a6dfe pushed by khosravipasha
39s master
master
39s
ggml: add Q1_0 1-bit quantization support (CPU) (#21273) Update Operations Documentation #6: Commit 2e1f0a8 pushed by khosravipasha
49s master
master
49s
initial Q1_0 Metal backend Update Operations Documentation #5: Pull request #14 synchronize by khosravipasha
44s q1-metal
q1-metal
44s
tuning q1_0 metal kernels Update Operations Documentation #4: Commit 0776cd2 pushed by khosravipasha
40s q1-metal
q1-metal
40s
models : move the token embedding norms to the first layer (#20943) Update Operations Documentation #3: Commit 9f102a1 pushed by khosravipasha
39s master
master
39s
Merge pull request #1 from PrismML-Eng/mmq Update Operations Documentation #2: Commit bc8122e pushed by khosravipasha
39s v0.0.2-prism
v0.0.2-prism
39s
CANN: support flash attention for head dim not multiple of 16, fix AL… Update Operations Documentation #1: Commit 07ba6d2 pushed by khosravipasha
32s master
master
32s