Skip to content

Actions: l3utterfly/llama.cpp

Actions

Release

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
release.yml
13 workflow runs
13 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: remove shell call from vulkan-shaders-gen tool, revert file c… Release #13: Commit a19bd6f pushed by l3utterfly
Queued master
master
Queued
ggml-hexagon: respect input size when getting/setting tensor data (#1… Release #12: Commit 13002a0 pushed by l3utterfly
1d 0h 0m 2s master
master
1d 0h 0m 2s
llama: fix leaked buffers for mmap + split files (#16765) Release #11: Commit 945501f pushed by l3utterfly
1d 0h 0m 2s master
master
1d 0h 0m 2s
ci: update vulkan ci (#16294) Release #10: Commit f09aefa pushed by l3utterfly
52m 10s master
master
52m 10s
sampling : optimize dist sampler (#15704) Release #9: Commit cdedb70 pushed by l3utterfly
49m 51s master
master
49m 51s
cuda: refactored ssm_scan and use CUB (#13291) Release #8: Commit 79c1160 pushed by l3utterfly
58m 12s master
master
58m 12s
embeddings: fix extraction of CLS pooling results (#14927) Release #7: Commit a118d80 pushed by l3utterfly
1h 7m 20s master
master
1h 7m 20s
llama : add jinja template for rwkv-world (#14665) Release #6: Commit 0d92267 pushed by l3utterfly
54m 29s master
master
54m 29s
readme : add hot PRs (#14636) Release #5: Commit aaa088d pushed by l3utterfly
1h 4m 25s master
master
1h 4m 25s
vulkan: increase LOAD_VEC_A to 8 (IQ1/IQ2) or 4 (IQ3) (#14485) Release #4: Commit 6491d6e pushed by l3utterfly
54m 47s master
master
54m 47s
model : gemma3n text-only (#14400) Release #3: Commit 8846aac pushed by l3utterfly
1h 0m 24s master
master
1h 0m 24s
opencl: add backend_synchronize (#13939) Release #2: Commit 71e74a3 pushed by l3utterfly
53m 56s master
master
53m 56s
CANN: Support MOE Model MUL_MAT_ID (#13042) Release #1: Commit 33d7aed pushed by l3utterfly
55m 30s master
master
55m 30s