Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
28,656 workflow run results
28,656 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA… Server #12053: Commit 02082f1 pushed by ngxson
9m 16s master
master
9m 16s
clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA… CI #20658: Commit 02082f1 pushed by ngxson
44m 24s master
master
44m 24s
clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA… EditorConfig Checker #23174: Commit 02082f1 pushed by ngxson
16s master
master
16s
Add support for new gfx1200 and gfx1201 targets Pull Request Labeler #9357: Pull request #12372 synchronize by slojosic-amd
12s
12s
SYCL: implement memset ggml backend buffer interface Server #12052: Pull request #12580 synchronize by qnixsynapse
8m 2s sycl/memset
sycl/memset
8m 2s
SYCL: implement memset ggml backend buffer interface CI #20657: Pull request #12580 synchronize by qnixsynapse
41m 0s sycl/memset
sycl/memset
41m 0s
SYCL: implement memset ggml backend buffer interface EditorConfig Checker #23173: Pull request #12580 synchronize by qnixsynapse
17s sycl/memset
sycl/memset
17s
SYCL: implement memset ggml backend buffer interface Pull Request Labeler #9356: Pull request #12580 synchronize by qnixsynapse
10s
10s
convert : fix squeeze for ssm_conv tensors (#12573) EditorConfig Checker #23172: Commit df4d20c pushed by compilade
17s master
master
17s
convert : fix squeeze for ssm_conv tensors (#12573) flake8 Lint #17746: Commit df4d20c pushed by compilade
36s master
master
36s
convert : fix squeeze for ssm_conv tensors (#12573) Python Type-Check #2157: Commit df4d20c pushed by compilade
1m 16s master
master
1m 16s
convert : fix squeeze for ssm_conv tensors (#12573) Python check requirements.txt #2738: Commit df4d20c pushed by compilade
2m 59s master
master
2m 59s
Fix T5Encoder model handling. Server #12051: Pull request #12590 opened by HighDoping
9m 59s HighDoping:master
HighDoping:master
9m 59s
Fix T5Encoder model handling. EditorConfig Checker #23171: Pull request #12590 opened by HighDoping
33s HighDoping:master
HighDoping:master
33s
Fix T5Encoder model handling. CI #20656: Pull request #12590 opened by HighDoping
2h 15m 46s HighDoping:master
HighDoping:master
2h 15m 46s
Fix T5Encoder model handling. Pull Request Labeler #9355: Pull request #12590 opened by HighDoping
14s
14s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp EditorConfig Checker #23170: Pull request #12326 synchronize by jeffzhou2000
17s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
17s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp Server #12050: Pull request #12326 synchronize by jeffzhou2000
8m 13s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
8m 13s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp CI #20655: Pull request #12326 synchronize by jeffzhou2000
46m 0s jeffzhou2000:pr_to_upstream
jeffzhou2000:pr_to_upstream
46m 0s
PR: Refine ggml-hexagon backend(Qualcomm Hexagon NPU backend) for latest ggml,whisper.cpp,llama.cpp Pull Request Labeler #9354: Pull request #12326 synchronize by jeffzhou2000
9s
9s
Supporting Velvet model Pull Request Labeler #9353: Pull request #11716 synchronize by fbuciuni90
12s
12s
ggml : fix MUL_MAT_ID repack with Q8_K (#12544) CI #20653: Commit 5ed38b6 pushed by ggerganov
48m 23s master
master
48m 23s
ggml : fix MUL_MAT_ID repack with Q8_K (#12544) Server #12048: Commit 5ed38b6 pushed by ggerganov
8m 6s master
master
8m 6s
ggml : fix MUL_MAT_ID repack with Q8_K (#12544) EditorConfig Checker #23168: Commit 5ed38b6 pushed by ggerganov
18s master
master
18s
Simplify and improve CUDA graphs through use of indirect copy pointers EditorConfig Checker #23167: Pull request #9017 synchronize by agray3
16s agray3:ag_indirect_copy_dest
agray3:ag_indirect_copy_dest
16s