Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
9,406 workflow run results
9,406 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: optimize rms_norm, and allow the work to spread across multiple SMs CI #26019: Pull request #15281 opened by jeffbolznv
1h 6m 6s jeffbolznv:rms_norm_atomic_add
jeffbolznv:rms_norm_atomic_add
1h 6m 6s
arm64: add i8mm route with SVE ggml_vec_dot_q4_K_q8_K and ggml_vec_dot_q6_K_… CI #26018: Pull request #15277 synchronize by fj-y-saito
1h 3m 42s fj-y-saito:feat-sve-i8mm-q4_K_quantization
fj-y-saito:feat-sve-i8mm-q4_K_quantization
1h 3m 42s
gpt-oss: implement harmony parsing CI #26017: Pull request #15181 synchronize by aldehir
1h 3m 6s aldehir:feature/harmony-parser
aldehir:feature/harmony-parser
1h 3m 6s
finetune: SGD optimizer, more CLI args CI #26016: Pull request #13873 synchronize by graehl
1h 14m 21s graehl:finelayer
graehl:finelayer
1h 14m 21s
arm64: add i8mm route with SVE ggml_vec_dot_q4_K_q8_K and ggml_vec_dot_q6_K_… CI #26015: Pull request #15277 opened by fj-y-saito
1h 5m 8s fj-y-saito:feat-sve-i8mm-q4_K_quantization
fj-y-saito:feat-sve-i8mm-q4_K_quantization
1h 5m 8s
HIP: disable sync warp shuffel operators from clr amd_warp_sync_funct… CI #26010: Commit b049315 pushed by IMbackK
1h 13m 52s master
master
1h 13m 52s
Q6_K - Block Interleaving Implementation for x86 SIMD (AVX512/AVX2) CI #26007: Pull request #15275 opened by Srihari-mcw
1h 5m 8s Srihari-mcw:block_interleaving_implementation_of_q6k
Srihari-mcw:block_interleaving_implementation_of_q6k
1h 5m 8s
HIP: disable sync warp shuffel operators from clr amd_warp_sync_functions.h CI #26006: Pull request #15273 opened by IMbackK
1h 14m 51s IMbackK:shfl
IMbackK:shfl
1h 14m 51s
opencl: add initial mxfp4 support via mv CI #26005: Pull request #15270 opened by lhez
1h 3m 32s CodeLinaro:mul-mv-mxfp4
CodeLinaro:mul-mv-mxfp4
1h 3m 32s
ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others) CI #26004: Pull request #15188 synchronize by Tak-RS
1h 10m 47s Tak-RS:fix/rpc-chunked-io
Tak-RS:fix/rpc-chunked-io
1h 10m 47s
vulkan: fuse adds CI #26003: Pull request #15252 synchronize by jeffbolznv
1h 7m 54s jeffbolznv:fuse_add
jeffbolznv:fuse_add
1h 7m 54s
vulkan: perf_logger improvements CI #26002: Pull request #15246 synchronize by jeffbolznv
1h 11m 2s jeffbolznv:perf_logger_matmul
jeffbolznv:perf_logger_matmul
1h 11m 2s
sycl: Fix and disable more configurations of mul_mat (#15151) CI #26000: Commit f4586ee pushed by Rbiessy
1h 4m 37s master
master
1h 4m 37s
ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others) CI #25999: Pull request #15188 synchronize by Tak-RS
1h 7m 24s Tak-RS:fix/rpc-chunked-io
Tak-RS:fix/rpc-chunked-io
1h 7m 24s
sycl: Fix and disable more configurations of mul_mat CI #25998: Pull request #15151 synchronize by Rbiessy
1h 19m 11s Rbiessy:romain/fix_more_mul_mat
Rbiessy:romain/fix_more_mul_mat
1h 19m 11s
opencl: allow mixed f16/f32 add (#15140) CI #25997: Commit 60a7658 pushed by lhez
1h 23m 33s master
master
1h 23m 33s
CUDA cmake: add -lineinfo for easier debug (#15260) CI #25996: Commit efe3a90 pushed by am17an
1h 17m 41s master
master
1h 17m 41s
CUDA: Optimize reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n CI #25995: Pull request #15132 synchronize by ORippler
1h 19m 31s ORippler:osimons/optimize_reduce_rows_f32
ORippler:osimons/optimize_reduce_rows_f32
1h 19m 31s
CUDA: Optimize reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n CI #25994: Pull request #15132 synchronize by ORippler
33m 23s ORippler:osimons/optimize_reduce_rows_f32
ORippler:osimons/optimize_reduce_rows_f32
33m 23s
Apple NPU acceleration integrated into llama.cpp, using MiniCPM-V 4.0 as an example. CI #25993: Pull request #15262 synchronize by tc-mb
1h 9m 26s tc-mb:Integrate-ANE-support-into-llama.cpp
tc-mb:Integrate-ANE-support-into-llama.cpp
1h 9m 26s
CANN: GGML_OP_CPY optimization (#15070) CI #25992: Commit bbd57b7 pushed by hipudding
1h 10m 38s master
master
1h 10m 38s
CANN: GGML_OP_CPY optimization CI #25988: Pull request #15070 synchronize by noemotiovon
1h 3m 46s noemotiovon:cpy_opti
noemotiovon:cpy_opti
1h 3m 46s
CUDA cmake: add compiler flag to add lineinfo CI #25987: Pull request #15260 opened by am17an
1h 7m 16s am17an:cuda_cmake_add_debug
am17an:cuda_cmake_add_debug
1h 7m 16s
Fixes #15247 | Update chat.cpp to support (at least) qwen3 reasoning + tool_choice = required CI #25984: Pull request #15248 synchronize by ExtReMLapin
1h 4m 54s ExtReMLapin:fix_qwen_reasoning_tool_calling_required
ExtReMLapin:fix_qwen_reasoning_tool_calling_required
1h 4m 54s
musa: fix build warnings CI #25983: Pull request #15258 synchronize by yeahdongcn
1h 24m 5s makllama:xd/fix_new_warn
makllama:xd/fix_new_warn
1h 24m 5s
ProTip! You can narrow down the results and go further in time using created:<2025-08-12 or the other filters available.