Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
4,152 workflow run results
4,152 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

metal : fix default.metallib build (#12224) CI #20071: Commit d6c95b0 pushed by danbev
35m 59s master
master
35m 59s
metal : simplify kernel arguments using a struct (#3229) CI #20070: Pull request #12194 synchronize by BB-fat
38m 17s BB-fat:metal-simplify-kernel-args
BB-fat:metal-simplify-kernel-args
38m 17s
opencl: Noncontiguous norm, rms_norm, disable fp16 for some ops… CI #20069: Commit d76a86d pushed by ericcurtin
38m 53s master
master
38m 53s
cmake : fix undefined reference errors for std::filesystem in ggml (#… CI #20068: Commit 776f9e5 pushed by ericcurtin
41m 57s master
master
41m 57s
tests: use adaptive number of threads CI #20067: Pull request #12236 opened by JohannesGaessler
40m 58s JohannesGaessler:test-better-nthreads
JohannesGaessler:test-better-nthreads
40m 58s
sync: minja (support QwQ-32B) CI #20066: Pull request #12235 opened by ochafik
48m 16s ochafik:sync-minja-6
ochafik:sync-minja-6
48m 16s
CUDA/HIP: refractor mmqv to unify the calculation of nwarps and rows per block between host and device code. CI #20065: Pull request #12177 synchronize by IMbackK
49m 46s IMbackK:refactor_mmqv
IMbackK:refactor_mmqv
49m 46s
CUDA/HIP: refractor mmqv to unify the calculation of nwarps and rows per block between host and device code. CI #20064: Pull request #12177 synchronize by IMbackK
4m 46s IMbackK:refactor_mmqv
IMbackK:refactor_mmqv
4m 46s
tool-call: add support for tool-calls using Model Context Protocol CI #20063: Pull request #11556 synchronize by bandoti
44m 49s bandoti:llamacli-tools
bandoti:llamacli-tools
44m 49s
server: log original chat template parsing error CI #20062: Pull request #12233 opened by CISC
45m 55s CISC:server-log-minja-error
CISC:server-log-minja-error
45m 55s
Fix HIP rocWMMA CI build break CI #20061: Pull request #12230 opened by hjc4869
49m 35s master
master
49m 35s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) CI #20060: Pull request #12181 synchronize by ggerganov
41m 16s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
41m 16s
CUDA: fix FA logic for PTX 7.0 and CC >= 7.5 (#12222) CI #20059: Commit 5220a16 pushed by JohannesGaessler
42m 47s master
master
42m 47s
SYCL: Rename oneMKL to oneMath CI #20058: Pull request #12192 synchronize by Rbiessy
39m 10s Rbiessy:romain/rename_onemath
Rbiessy:romain/rename_onemath
39m 10s
Optimized DeepSeek V2/V3 implementation (MLA + flash attention) CI #20057: Pull request #12227 synchronize by jukofyork
43m 12s mla-with-flash-attention
mla-with-flash-attention
43m 12s
Optimized DeepSeek V2/V3 implementation (MLA + flash attention) CI #20056: Pull request #12227 opened by jukofyork
49m 54s mla-with-flash-attention
mla-with-flash-attention
49m 54s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) CI #20055: Pull request #12181 synchronize by ggerganov
40m 48s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
40m 48s
CUDA: Improve flash decoding kernel GPU occupancy for BS=1 case CI #20054: Pull request #12183 synchronize by gaugarg-nv
40m 2s gaugarg-nv:flash_decoding_improvement
gaugarg-nv:flash_decoding_improvement
40m 2s
HIP: rocWMMA documentation and enabling in workflow builds (#12179) CI #20053: Commit 3ffbbd5 pushed by JohannesGaessler
40m 35s master
master
40m 35s
metal : fix default.metallib build CI #20052: Pull request #12224 opened by danbev
39m 34s danbev:metal-default-metal-lib-build
danbev:metal-default-metal-lib-build
39m 34s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) CI #20051: Pull request #12181 synchronize by ggerganov
48m 37s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
48m 37s
CUDA: fix FA logic for PTX 7.0 and CC >= 7.5 CI #20050: Pull request #12222 opened by JohannesGaessler
39m 16s JohannesGaessler:cuda-fix-fattn-logic
JohannesGaessler:cuda-fix-fattn-logic
39m 16s
opencl: use OpenCL C standard supported by the device CI #20049: Pull request #12221 opened by linehill
42m 34s linehill:ocl-pick-cl-std
linehill:ocl-pick-cl-std
42m 34s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) CI #20048: Pull request #12181 synchronize by ggerganov
41m 29s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
41m 29s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) CI #20047: Pull request #12181 synchronize by ggerganov
2m 2s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
2m 2s