Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
9,053 workflow run results
9,053 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Q2k interleaving implementation - x86/x64 SIMD CI #25524: Pull request #14373 synchronize by Srihari-mcw
3h 0m 35s Srihari-mcw:q2k_interleaving_implementation
Srihari-mcw:q2k_interleaving_implementation
3h 0m 35s
Support MiniCPM-V 4.0 CI #25523: Pull request #14983 opened by tc-mb
1h 48m 6s tc-mb:support-MiniCPM-V-4
tc-mb:support-MiniCPM-V-4
1h 48m 6s
graph : reduce splits for recurrent and hybrid models (#14825) CI #25522: Commit 66625a5 pushed by ggerganov
3h 27m 44s master
master
3h 27m 44s
ggml: aarch64: Implement SVE Kernels for Int 8 Quantization CI #25521: Pull request #14117 synchronize by Vithulep
2h 36m 28s Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
2h 36m 28s
ggml: initial IBM zDNN backend CI #25520: Pull request #14975 synchronize by taronaeo
2h 19m 27s taronaeo:feat/backend-zdnn
taronaeo:feat/backend-zdnn
2h 19m 27s
vulkan: Use coopmat2 for conv2d CI #25519: Pull request #14982 opened by jeffbolznv
1h 51m 50s jeffbolznv:conv_coopmat2
jeffbolznv:conv_coopmat2
1h 51m 50s
Add LLaDA 8b Diffusion model CI #25517: Pull request #14771 synchronize by am17an
2h 49m 9s am17an:add_llada_8b
am17an:add_llada_8b
2h 49m 9s
CUDA: add set CI #25516: Pull request #14980 opened by jeemzz147
2h 27m 39s jeemzz147:cuda/set
jeemzz147:cuda/set
2h 27m 39s
vulkan: optimizations for direct convolution CI #25515: Pull request #14933 synchronize by jeffbolznv
1h 47m 30s jeffbolznv:conv_opt
jeffbolznv:conv_opt
1h 47m 30s
docker : add cann build pipline CI #25514: Pull request #14591 synchronize by diannaojiang
2h 37m 35s diannaojiang:docker-cann
diannaojiang:docker-cann
2h 37m 35s
ggml: WebGPU backend host improvements and style fixing CI #25511: Pull request #14978 opened by reeselevine
1h 4m 14s reeselevine:master
reeselevine:master
1h 4m 14s
opencl: add mul_mat_f32_f32_l4_lm and mul_mat_f16_f32_l4_lm (#14809) CI #25510: Commit 6e67254 pushed by max-krasnyansky
1h 1m 56s master
master
1h 1m 56s
server: Add openai-style logit_bias support CI #25509: Pull request #14946 synchronize by lukasstraub2
2h 13m 43s lukasstraub2:openai_logit_bias
lukasstraub2:openai_logit_bias
2h 13m 43s
quantize : fix using combined imatrix GGUFs (multiple datasets) (#14973) CI #25507: Commit e9192be pushed by CISC
1h 17m 11s master
master
1h 17m 11s
ggml: initial IBM zDNN backend CI #25506: Pull request #14975 synchronize by taronaeo
1h 20m 5s taronaeo:feat/backend-zdnn
taronaeo:feat/backend-zdnn
1h 20m 5s
fix: using combined imatrix to quantise models triggers an error #14952 CI #25505: Pull request #14973 opened by EAddario
2h 14m 43s EAddario:14952-fix
EAddario:14952-fix
2h 14m 43s
server : add support for embd_normalize parameter (#14964) CI #25504: Commit 41e78c5 pushed by danbev
3h 32m 12s master
master
3h 32m 12s
llama-server : implement universal assisted decoding CI #25503: Pull request #12635 synchronize by g2mt
2h 5m 36s g2mt:master
g2mt:master
2h 5m 36s
Optimize l2_norm_f32 op with SIMD CI #25500: Pull request #14970 opened by TIKki43
2h 24m 12s TIKki43:perf/l2-norm-optimize
TIKki43:perf/l2-norm-optimize
2h 24m 12s
HIP: enable mfma mmq on gfx908 and gfx90a for select datatypes and sh… CI #25499: Commit ad4a700 pushed by IMbackK
3h 27m 13s master
master
3h 27m 13s
sync : ggml CI #25498: Commit e32a4ec pushed by ggerganov
3h 9m 42s master
master
3h 9m 42s
vulkan: optimizations for direct convolution CI #25497: Pull request #14933 synchronize by jeffbolznv
3h 12m 47s jeffbolznv:conv_opt
jeffbolznv:conv_opt
3h 12m 47s
Refactor: Merge build_moe_ffn_from_probs function into build_moe_ffn CI #25496: Pull request #14968 opened by wdl339
2h 58m 26s wdl339:build-moe-refactor
wdl339:build-moe-refactor
2h 58m 26s
CUDA: skip masked KV slices for all FA kernels (#14924) CI #25495: Commit 92b8810 pushed by JohannesGaessler
2h 37m 13s master
master
2h 37m 13s
Q2k interleaving implementation - x86/x64 SIMD CI #25494: Pull request #14373 synchronize by Srihari-mcw
2h 49m 32s Srihari-mcw:q2k_interleaving_implementation
Srihari-mcw:q2k_interleaving_implementation
2h 49m 32s
ProTip! You can narrow down the results and go further in time using created:<2025-07-30 or the other filters available.