Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
583 workflow run results
583 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : default sampling changes + greedy update CI #16019: Pull request #9897 synchronize by ggerganov
33m 23s gg/llama-remove-softmax
gg/llama-remove-softmax
33m 23s
llama : default sampling changes + greedy update CI #16018: Pull request #9897 synchronize by ggerganov
32m 22s gg/llama-remove-softmax
gg/llama-remove-softmax
32m 22s
rpc : backend refactoring CI #16017: Pull request #9912 synchronize by rgerganov
48m 52s rgerganov:rpc-refactor
rgerganov:rpc-refactor
48m 52s
llama : infill sampling handle very long tokens CI #16016: Pull request #9924 synchronize by ggerganov
54m 22s gg/infill-4
gg/infill-4
54m 22s
llama : infill sampling handle very long tokens CI #16015: Pull request #9924 opened by ggerganov
50m 44s gg/infill-4
gg/infill-4
50m 44s
llama : adds llama-grammar memoization stacks (#4218) CI #16014: Pull request #9833 synchronize by clarismiranda
1h 23m 48s clarismiranda:grammar-memo
clarismiranda:grammar-memo
1h 23m 48s
sample: maintain token count in penalty sampler context CI #16011: Pull request #9922 opened by kylo5aby
56m 36s kylo5aby:penalty-sample
kylo5aby:penalty-sample
56m 36s
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels CI #16010: Pull request #9921 synchronize by chaxu01
49m 55s chaxu01:feature/online-flow
chaxu01:feature/online-flow
49m 55s
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels CI #16009: Pull request #9921 opened by chaxu01
40m 28s chaxu01:feature/online-flow
chaxu01:feature/online-flow
40m 28s
rpc : backend refactoring CI #16008: Pull request #9912 synchronize by rgerganov
44m 1s rgerganov:rpc-refactor
rgerganov:rpc-refactor
44m 1s
llama : adds llama-grammar memoization stacks (#4218) CI #16007: Pull request #9833 synchronize by clarismiranda
59m 51s clarismiranda:grammar-memo
clarismiranda:grammar-memo
59m 51s
vulkan : add backend registry / device interfaces (#9721) CI #16006: Commit f010b77 pushed by slaren
59m 0s master
master
59m 0s
Add Intel Advanced Matrix Extensions (AMX) support to ggml CI #16005: Pull request #8998 synchronize by mingfeima
1h 18m 45s pr_add_intel_amx_support
pr_add_intel_amx_support
1h 18m 45s
Add Intel Advanced Matrix Extensions (AMX) support to ggml CI #16004: Pull request #8998 synchronize by mingfeima
11m 4s pr_add_intel_amx_support
pr_add_intel_amx_support
11m 4s
vulkan : add backend registry / device interfaces CI #16003: Pull request #9721 synchronize by slaren
1h 31m 31s sl/vulkan-reg-2
sl/vulkan-reg-2
1h 31m 31s
fix: allocating CPU buffer with size 0 (#9917) CI #16002: Commit 2194200 pushed by slaren
1h 12m 53s master
master
1h 12m 53s
fix: allocating CPU buffer with size 0 CI #16001: Pull request #9917 opened by giladgd
54m 8s giladgd:fix0alloc
giladgd:fix0alloc
54m 8s
fix: use vm_allocate to allocate CPU backend buffer on macOS (#9875) CI #16000: Commit 73afe68 pushed by slaren
2h 3m 56s master
master
2h 3m 56s
llama : suppress conversion from 'size_t' to 'int' (#9046) CI #15999: Commit 9e04102 pushed by ggerganov
1h 29m 35s master
master
1h 29m 35s
[SYCL] Add SYCL Backend registry, device and Event Interfaces CI #15998: Pull request #9705 synchronize by OuadiElfarouki
1h 10m 20s OuadiElfarouki:sycl_async_data_load
OuadiElfarouki:sycl_async_data_load
1h 10m 20s
grammar : fix JSON Schema for string regex with top-level alt. (#9903) CI #15997: Commit 66c2c93 pushed by ggerganov
2h 23m 8s master
master
2h 23m 8s
rpc : backend refactoring CI #15996: Pull request #9912 opened by rgerganov
52m 9s rgerganov:rpc-refactor
rgerganov:rpc-refactor
52m 9s
llama : bump max layers from 512 to 1024 CI #15994: Pull request #9910 opened by nicoboss
57m 32s nicoboss:bump-max-layers
nicoboss:bump-max-layers
57m 32s
llama : rename batch_all to batch CI #15993: Pull request #8881 synchronize by danbev
1h 5m 4s danbev:rename-batch-all
danbev:rename-batch-all
1h 5m 4s
llama : add tensor name for "result_norm" (#9907) CI #15992: Commit 10433e8 pushed by ggerganov
2h 12m 40s master
master
2h 12m 40s