Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
5,164 workflow run results
5,164 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #21000: Pull request #12326 synchronize by jeffzhou2000
40m 44s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
40m 44s
sycl:remove redundant memcopy in function ggml_backend_sycl_buffer_set_tensor CI #20999: Pull request #12734 opened by jeffzhou2000
40m 27s jeffzhou2000:fix_code_in_ggmlsycl
jeffzhou2000:fix_code_in_ggmlsycl
40m 27s
CANN: fix typo in ggml-cann CI #20998: Pull request #12733 opened by jeffzhou2000
41m 24s jeffzhou2000:fix_typo_in_ggmlcann
jeffzhou2000:fix_typo_in_ggmlcann
41m 24s
sync : ggml CI #20997: Pull request #12732 opened by ggerganov
1h 1m 18s sync-ggml-25-04-03
sync-ggml-25-04-03
1h 1m 18s
CANN: Refactor to reduce duplicate code CI #20996: Pull request #12731 opened by hipudding
1h 4m 18s hipudding:refactor
hipudding:refactor
1h 4m 18s
fix MUSA compiler warning (#12704) CI #20995: Commit 193c3e0 pushed by CISC
1h 0m 35s master
master
1h 0m 35s
CANN: Support operator SIN COS ARGMAX (#12709) CI #20994: Commit 65cfe13 pushed by hipudding
53m 44s master
master
53m 44s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #20991: Pull request #12326 synchronize by jeffzhou2000
43m 39s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
43m 39s
DeepSeek V2/V3 with -mla option CI #20990: Pull request #12725 synchronize by jukofyork
44m 31s mainline-llama-cpp-master--mla
mainline-llama-cpp-master--mla
44m 31s
DeepSeek V2/V3 with -mla option CI #20989: Pull request #12725 synchronize by jukofyork
36m 47s mainline-llama-cpp-master--mla
mainline-llama-cpp-master--mla
36m 47s
[CANN]Support operator SIN COS ARGMAX CI #20988: Pull request #12709 synchronize by noemotiovon
45m 47s noemotiovon:opt_support
noemotiovon:opt_support
45m 47s
Update llama-quant.cpp llama_tensor_get_type with DeepSeek friendly modifications CI #20986: Pull request #12727 synchronize by bartowski1182
46m 38s bartowski1182:quant_types
bartowski1182:quant_types
46m 38s
Update llama-quant.cpp llama_tensor_get_type with DeepSeek friendly modifications CI #20985: Pull request #12727 synchronize by bartowski1182
10m 14s bartowski1182:quant_types
bartowski1182:quant_types
10m 14s
Update llama-quant.cpp llama_tensor_get_type with DeepSeek friendly modifications CI #20984: Pull request #12727 opened by bartowski1182
3m 47s bartowski1182:quant_types
bartowski1182:quant_types
3m 47s
DeepSeek V2/V3 with -mla option CI #20983: Pull request #12725 synchronize by jukofyork
42m 2s mainline-llama-cpp-master--mla
mainline-llama-cpp-master--mla
42m 2s
Simplify and improve CUDA graphs through use of indirect copy pointer… CI #20982: Commit 3f9da22 pushed by slaren
1h 4m 47s master
master
1h 4m 47s
[CANN]Support operator SIN COS ARGMAX CI #20981: Pull request #12709 synchronize by noemotiovon
42m 20s noemotiovon:opt_support
noemotiovon:opt_support
42m 20s
CANN: Fix failed test cases (#12708) CI #20980: Commit 2a0dc97 pushed by hipudding
45m 59s master
master
45m 59s
opencl: use max_alloc_size in backend ctx instead of querying again… CI #20979: Commit 97a20c0 pushed by max-krasnyansky
42m 36s master
master
42m 36s
DeepSeek V2/V3 with -mla option CI #20978: Pull request #12725 opened by jukofyork
43m 7s mainline-llama-cpp-master--mla
mainline-llama-cpp-master--mla
43m 7s
vulkan: Use unclamped loads for flash attention mask CI #20977: Pull request #12720 synchronize by jeffbolznv
57m 7s jeffbolznv:flash_mask
jeffbolznv:flash_mask
57m 7s
vulkan: Implement split_k for coopmat2 flash attention. (#12627) CI #20976: Commit f01bd02 pushed by jeffbolznv
51m 16s master
master
51m 16s
vulkan: Implement split_k for coopmat2 flash attention. CI #20975: Pull request #12627 synchronize by jeffbolznv
1h 25m 43s jeffbolznv:flash_split_k
jeffbolznv:flash_split_k
1h 25m 43s
cmake: remove caching from vulkan coopmat checks (#12719) CI #20974: Commit 6f3bd38 pushed by bandoti
1h 29m 14s master
master
1h 29m 14s
vulkan: Implement split_k for coopmat2 flash attention. CI #20973: Pull request #12627 synchronize by jeffbolznv
9m 38s jeffbolznv:flash_split_k
jeffbolznv:flash_split_k
9m 38s
ProTip! You can narrow down the results and go further in time using created:<2025-04-02 or the other filters available.