Skip to content

Actions: zyang-dev/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
Workflows are not currently being run on this fork due to the scale of GitHub Actions usage. A repository maintainer can choose to re-enable these.
35 workflow runs
35 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Gate copying split inputs with the consuming graph nodes' flag GGML_T… CI (cann) #9: Commit 77d26ac pushed by zyang-dev
Failure sched-unused-split-inputs
sched-unused-split-inputs
Failure
Build Actions Cache Build Actions Cache #4: Scheduled
24s master
master
24s
Build Actions Cache Build Actions Cache #3: Scheduled
24s master
master
24s
Update Winget Package Update Winget Package #1: Scheduled
1s master
master
1s
Publish Docker image Publish Docker image #1: Scheduled
12h 19m 5s master
master
12h 19m 5s
Build Actions Cache Build Actions Cache #2: Scheduled
27s master
master
27s
Close inactive issues Close inactive issues #1: Scheduled
11s master
master
11s
CI (apple - daily) CI (apple - daily) #1: Scheduled
31m 7s master
master
31m 7s
Build Actions Cache Build Actions Cache #1: Scheduled
6m 41s master
master
6m 41s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… Python check requirements.txt #4: Commit b3d57de pushed by zyang-dev
3m 3s rpc_nccl
rpc_nccl
3m 3s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… Update Operations Documentation #4: Commit b3d57de pushed by zyang-dev
46s rpc_nccl
rpc_nccl
46s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… Python Type-Check #4: Commit b3d57de pushed by zyang-dev
5m 27s rpc_nccl
rpc_nccl
5m 27s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… Check Pre-Tokenizer Hashes #4: Commit b3d57de pushed by zyang-dev
1m 38s rpc_nccl
rpc_nccl
1m 38s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… CI (cann) #8: Commit b3d57de pushed by zyang-dev
Failure rpc_nccl-test
rpc_nccl-test
Failure
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… Python check requirements.txt #3: Commit b3d57de pushed by zyang-dev
3m 19s rpc_nccl-test
rpc_nccl-test
3m 19s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… Check Pre-Tokenizer Hashes #3: Commit b3d57de pushed by zyang-dev
1m 45s rpc_nccl-test
rpc_nccl-test
1m 45s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… Update Operations Documentation #3: Commit b3d57de pushed by zyang-dev
1m 15s rpc_nccl-test
rpc_nccl-test
1m 15s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… Python Type-Check #3: Commit b3d57de pushed by zyang-dev
11m 17s rpc_nccl-test
rpc_nccl-test
11m 17s
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… CI (cann) #7: Commit b3d57de pushed by zyang-dev
Failure rpc_nccl-test
rpc_nccl-test
Failure
set maxCTAs in ncclConfig_t to 8 for dgx spark in ggml_backend_cuda_c… CI (cann) #6: Commit 91dd6f8 pushed by zyang-dev
Failure rpc_nccl
rpc_nccl
Failure
Change ggml_backend_comm_get_unique_id_t and ggml_backend_comm_init_r… CI (cann) #5: Commit 9fe4f1f pushed by zyang-dev
Failure rpc_nccl
rpc_nccl
Failure
reuse ggml_backend_cuda_comm_allreduce_nccl for per-rank communicator… Update Operations Documentation #2: Commit ce3d4c8 pushed by zyang-dev
2m 3s rpc_nccl
rpc_nccl
2m 3s
reuse ggml_backend_cuda_comm_allreduce_nccl for per-rank communicator… Copilot Setup Steps #2: Commit ce3d4c8 pushed by zyang-dev
1m 46s rpc_nccl
rpc_nccl
1m 46s
reuse ggml_backend_cuda_comm_allreduce_nccl for per-rank communicator… Python Type-Check #2: Commit ce3d4c8 pushed by zyang-dev
3m 11s rpc_nccl
rpc_nccl
3m 11s
reuse ggml_backend_cuda_comm_allreduce_nccl for per-rank communicator… Python check requirements.txt #2: Commit ce3d4c8 pushed by zyang-dev
3m 0s rpc_nccl
rpc_nccl
3m 0s