Skip to content

Actions: papamoose/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
49 workflow runs
49 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
GGML_CPU_ALL_VARIANTS=OFF allows arm64 builds to complete Check Pre-Tokenizer Hashes #49: Commit 8ad5b22 pushed by papamoose
1d 0h 0m 1s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
1d 0h 0m 1s
app : allow --version, --licenses & --help (#25054) Check Pre-Tokenizer Hashes #48: Commit 050ee92 pushed by papamoose
1d 0h 0m 1s master
master
1d 0h 0m 1s
GGML_CPU_ALL_VARIANTS=OFF allows arm64 builds to complete Check Pre-Tokenizer Hashes #47: Commit 2940398 pushed by papamoose
1d 0h 0m 2s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
1d 0h 0m 2s
ggml-cpu: use runtime SVE width in FWHT (#24059) Check Pre-Tokenizer Hashes #46: Commit 3571fa5 pushed by papamoose
1d 0h 0m 2s master
master
1d 0h 0m 2s
GGML_CPU_ALL_VARIANTS=OFF allows arm64 builds to complete Check Pre-Tokenizer Hashes #45: Commit 387b70b pushed by papamoose
1d 0h 0m 2s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
1d 0h 0m 2s
ci : limit trigger paths for the CPU workflow (#23938) Check Pre-Tokenizer Hashes #44: Commit 399739d pushed by papamoose
1d 0h 0m 1s master
master
1d 0h 0m 1s
attempt to build arm64 image Check Pre-Tokenizer Hashes #43: Commit b48f5ce pushed by papamoose
22m 53s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
22m 53s
opencl: generalize Adreno MoE kernels on M (#23449) Check Pre-Tokenizer Hashes #42: Commit 0f3cb3f pushed by papamoose
1m 12s master
master
1m 12s
attempt to build arm64 image Check Pre-Tokenizer Hashes #41: Commit a858977 pushed by papamoose
47m 44s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
47m 44s
hexagon: add support for TRI op (#22822) Check Pre-Tokenizer Hashes #40: Commit 9a532ae pushed by papamoose
1m 2s master
master
1m 2s
attempt to build arm64 image Check Pre-Tokenizer Hashes #39: Commit 59af8e1 pushed by papamoose
26m 46s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
26m 46s
hexagon: guard HMX clock request for v75+ platforms (#22377) Check Pre-Tokenizer Hashes #38: Commit b760272 pushed by papamoose
34m 3s master
master
34m 3s
Remove extra conditional check on debug mode. (#21798) Check Pre-Tokenizer Hashes #37: Commit bafae27 pushed by papamoose
1m 16s master
master
1m 16s
enable NCCL Check Pre-Tokenizer Hashes #36: Commit 8bea33c pushed by papamoose
23m 3s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
23m 3s
CUDA: skip compilation of superfluous FA kernels (#21768) Check Pre-Tokenizer Hashes #35: Commit ff5ef82 pushed by papamoose
22m 12s master
master
22m 12s
enable NCCL Check Pre-Tokenizer Hashes #34: Commit db73dcb pushed by papamoose
4m 35s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
4m 35s
ci: lower cuda12 floor to 12.8.1 for broader host compatibility (#21438) Check Pre-Tokenizer Hashes #33: Commit c08d28d pushed by papamoose
26m 1s master
master
26m 1s
enable NCCL Check Pre-Tokenizer Hashes #32: Commit 9e96c65 pushed by papamoose
6m 34s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
6m 34s
models : move the token embedding norms to the first layer (#20943) Check Pre-Tokenizer Hashes #31: Commit 9f102a1 pushed by papamoose
49s master
master
49s
add -DGGML_CPU_ARM_ARCH="armv8.2-a+dotprod+i8mm" Check Pre-Tokenizer Hashes #30: Commit ad0c537 pushed by papamoose
54s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
54s
vulkan: use graphics queue on AMD (#20551) Check Pre-Tokenizer Hashes #29: Commit 1a3d8ed pushed by papamoose
1m 4s master
master
1m 4s
add -DGGML_CPU_ARM_ARCH="armv8.2-a+dotprod+i8mm" Check Pre-Tokenizer Hashes #28: Commit b5defac pushed by papamoose
13m 14s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
13m 14s
common/parser: add GigaChatV3/3.1 models support (#19931) Check Pre-Tokenizer Hashes #27: Commit a8304b4 pushed by papamoose
56s master
master
56s
arm64 job name changed: build-arm64-ubuntu2404-cuda129 Check Pre-Tokenizer Hashes #26: Commit 50f2cc7 pushed by papamoose
5m 27s papamoose/cuda_arm64_docker_build
papamoose/cuda_arm64_docker_build
5m 27s
replace the magic nunber 768 by max work group size to support iGPU (… Check Pre-Tokenizer Hashes #25: Commit c17dce4 pushed by papamoose
53s master
master
53s