Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
4,025 workflow run results
4,025 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: double buffer scale caches CI #19977: Pull request #12188 opened by netrunnereve
40m 5s double_buffering
double_buffering
40m 5s
CUDA: Fix new mma detection for Turing cards with Volta PTX CI #19976: Pull request #12187 opened by neilmehta24
41m 31s neilmehta24:flash-attn-fix
neilmehta24:flash-attn-fix
41m 31s
llama : add xcframework build script CI #19974: Pull request #11996 synchronize by danbev
39m 30s danbev:xcframework-build-10747
danbev:xcframework-build-10747
39m 30s
CUDA: Improve flash decoding kernel GPU occupancy for BS=1 case CI #19973: Pull request #12183 synchronize by gaugarg-nv
42m 0s gaugarg-nv:flash_decoding_improvement
gaugarg-nv:flash_decoding_improvement
42m 0s
CUDA: Improve flash decoding kernel GPU occupancy for BS=1 case CI #19972: Pull request #12183 synchronize by gaugarg-nv
34m 47s gaugarg-nv:flash_decoding_improvement
gaugarg-nv:flash_decoding_improvement
34m 47s
tool-call: add support for tool-calls using Model Context Protocol CI #19971: Pull request #11556 synchronize by bandoti
41m 21s bandoti:llamacli-tools
bandoti:llamacli-tools
41m 21s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) CI #19970: Pull request #12181 synchronize by ggerganov
47m 1s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
47m 1s
ggml : portability fixes for VS 2017 (#12150) CI #19969: Commit 5bbe6a9 pushed by ggerganov
59m 47s master
master
59m 47s
CUDA: Improve flash decoding kernel GPU occupancy for BS=1 case CI #19968: Pull request #12183 synchronize by gaugarg-nv
48m 41s gaugarg-nv:flash_decoding_improvement
gaugarg-nv:flash_decoding_improvement
48m 41s
main: allow preloading conversation with -p and add -st / --single-tu… CI #19967: Commit 56d7a9f pushed by bandoti
57m 49s master
master
57m 49s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) CI #19966: Pull request #12181 synchronize by ggerganov
40m 53s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
40m 53s
llama : refactor llama_context, llama_kv_cache, llm_build_context (v2) CI #19965: Pull request #12181 opened by ggerganov
3m 56s gg/llama-kv-cache-v2
gg/llama-kv-cache-v2
3m 56s
main: allow preloading conversation with -p and add -st / --single-turn CI #19964: Pull request #12145 synchronize by CISC
39m 24s CISC:no-cnv-chat-template
CISC:no-cnv-chat-template
39m 24s
HIP: rocWMMA documentation and enabling in workflow builds CI #19963: Pull request #12179 opened by hjc4869
42m 10s ci-rocwmma
ci-rocwmma
42m 10s
main: allow preloading conversation with -p and add -st / --single-turn CI #19962: Pull request #12145 synchronize by CISC
38m 29s CISC:no-cnv-chat-template
CISC:no-cnv-chat-template
38m 29s
CUDA/HIP: refractor mmqv to unify the calculation of nwarps and rows per block between host and device code. CI #19961: Pull request #12177 synchronize by IMbackK
45m 53s IMbackK:refactor_mmqv
IMbackK:refactor_mmqv
45m 53s
main: allow preloading conversation with -p and add -st / --single-turn CI #19960: Pull request #12145 synchronize by CISC
43m 38s CISC:no-cnv-chat-template
CISC:no-cnv-chat-template
43m 38s
CUDA/HIP: refractor mmqv to unify the calculation of nwarps and rows per block between host and device code. CI #19959: Pull request #12177 synchronize by IMbackK
14m 21s IMbackK:refactor_mmqv
IMbackK:refactor_mmqv
14m 21s
CUDA/HIP: refractor mmqv to unify the calculation of nwarps and rows per block between host and device code. CI #19958: Pull request #12177 opened by IMbackK
1m 59s IMbackK:refactor_mmqv
IMbackK:refactor_mmqv
1m 59s
opencl: Fix ulong kernel args were set from int variables CI #19957: Pull request #12174 opened by linehill
40m 55s linehill:ocl-fix-args
linehill:ocl-fix-args
40m 55s
main: allow preloading conversation with -p and add -st / --single-turn CI #19956: Pull request #12145 synchronize by CISC
47m 42s CISC:no-cnv-chat-template
CISC:no-cnv-chat-template
47m 42s
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions CI #19955: Pull request #12154 synchronize by remyoudompheng
41m 17s remyoudompheng:optim-x86
remyoudompheng:optim-x86
41m 17s
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions CI #19954: Pull request #12154 synchronize by remyoudompheng
4m 7s remyoudompheng:optim-x86
remyoudompheng:optim-x86
4m 7s
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions CI #19953: Pull request #12154 synchronize by remyoudompheng
10m 45s remyoudompheng:optim-x86
remyoudompheng:optim-x86
10m 45s
server: fix deadly typo in response_format.json_schema.schema handl… CI #19952: Commit 1a24c46 pushed by ggerganov
43m 1s master
master
43m 1s