Skip to content

Actions: EAddario/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
83 workflow runs
83 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

opencl: mark argsort unsupported if cols exceed workgroup limit (#1… CI #58: Commit fb22dd0 pushed by EAddario
1h 4m 54s master
master
1h 4m 54s
vulkan: disable spirv-opt for bfloat16 shaders (#15352) CI #57: Commit ae532ea pushed by EAddario
1h 15m 54s master
master
1h 15m 54s
common : fix double bos, use common_chat_templates for add_bos and ad… CI #56: Commit 5e6229a pushed by EAddario
1h 29m 5s master
master
1h 29m 5s
cuda: refactored ssm_scan and use CUB (#13291) CI #55: Commit 79c1160 pushed by EAddario
1h 8m 39s master
master
1h 8m 39s
gguf-py : add Numpy MXFP4 de/quantization support (#15111) CI #54: Commit e54d41b pushed by EAddario
1h 4m 22s master
master
1h 4m 22s
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 (#15131) CI #53: Commit 1d72c84 pushed by EAddario
1h 7m 2s master
master
1h 7m 2s
llama : add gpt-oss (#15091) CI #52: Commit fd1234c pushed by EAddario
6h 0m 25s master
master
6h 0m 25s
vulkan: fix build when using glslang that does not support coopmat2 (… CI #51: Commit 5aa1105 pushed by EAddario
1h 18m 34s master
master
1h 18m 34s
opencl: add mul_mat_f32_f32_l4_lm and mul_mat_f16_f32_l4_lm (#14809) CI #50: Commit 6e67254 pushed by EAddario
1h 2m 11s master
master
1h 2m 11s
server : add support for embd_normalize parameter (#14964) CI #49: Commit 41e78c5 pushed by EAddario
1h 13m 3s master
master
1h 13m 3s
CUDA: add roll (#14919) CI #48: Commit 0a5036b pushed by EAddario
1h 2m 40s master
master
1h 2m 40s
vulkan: add ops docs (#14900) CI #47: Commit bf78f54 pushed by EAddario
1h 13m 14s master
master
1h 13m 14s
CANN: Implement GLU ops (#14884) CI #46: Commit 11dd5a4 pushed by EAddario
1h 3m 36s master
master
1h 3m 36s
musa: fix build warnings (unused variable) (#14869) CI #45: Commit 9b8f3c6 pushed by EAddario
1h 11m 25s master
master
1h 11m 25s
ggml-cpu : disable GGML_NNPA by default due to instability (#14880) CI #44: Commit c7f3169 pushed by EAddario
1h 13m 43s master
master
1h 13m 43s
ci : correct label refactor->refactoring (#14832) CI #43: Commit 221c0e0 pushed by EAddario
1h 2m 21s master
master
1h 2m 21s
ggml : model card yaml tab->2xspace (#14819) CI #42: Commit acd6cb1 pushed by EAddario
1h 3m 30s master
master
1h 3m 30s
imatrix : use GGUF to store importance matrices (#9400) CI #41: Commit 9008328 pushed by EAddario
1h 6m 33s master
master
1h 6m 33s
Documentation: Update build.md's Vulkan section (#14736) CI #40: Commit f0d4d17 pushed by EAddario
59m 18s master
master
59m 18s
llama : fix parallel processing for lfm2 (#14705) CI #39: Commit 086cf81 pushed by EAddario
58m 27s master
master
58m 27s
convert : only check for tokenizer folder if we need it (#14704) CI #38: Commit 4b91d6f pushed by EAddario
1h 1m 31s master
master
1h 1m 31s
quantize : fix minor logic flaw in --tensor-type (#14572) CI #37: Commit 982e347 pushed by EAddario
1h 7m 26s master
master
1h 7m 26s
model : support LiquidAI LFM2 hybrid family (#14620) CI #36: Commit f5e96b3 pushed by EAddario
1h 23m 56s master
master
1h 23m 56s
llama : remove ggml_cont where possible (#14568) CI #35: Commit 12f55c3 pushed by EAddario
1h 14m 20s master
master
1h 14m 20s
vulkan: Handle updated FA dim2/3 definition (#14518) CI #34: Commit a0374a6 pushed by EAddario
1h 18m 11s master
master
1h 18m 11s