Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
7,874 workflow run results
7,874 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml: aarch64: Implement SVE Kernels for Int 8 Quantization CI #23595: Pull request #14117 synchronize by Vithulep
1h 17m 17s Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
1h 17m 17s
Pass --keep to llama-server CI #23594: Pull request #14120 opened by MightyAlex200
59m 58s MightyAlex200:master
MightyAlex200:master
59m 58s
kv-cache : relax SWA masking condition CI #23593: Pull request #14119 opened by ggerganov
1h 0m 10s gg/swa-relax-masking
gg/swa-relax-masking
1h 0m 10s
ggml: aarch64: Implement SVE Kernels for Int 8 Quantization CI #23592: Pull request #14117 synchronize by Vithulep
1h 1m 12s Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
1h 1m 12s
llama-model : add dots.llm1 architecture support (#14044) CI #23591: Pull request #14118 synchronize by Noeda
1h 11m 52s Noeda:dots1_squished_squashy
Noeda:dots1_squished_squashy
1h 11m 52s
llama-model : add dots.llm1 architecture support (#14044) CI #23590: Pull request #14118 opened by Noeda
6m 33s Noeda:dots1_squished_squashy
Noeda:dots1_squished_squashy
6m 33s
vulkan: Track descriptor pools/sets per-context (#14109) CI #23589: Commit 1f7d50b pushed by 0cc4m
58m 45s master
master
58m 45s
ggml: aarch64: Implement SVE Kernels for Int 8 Quantization CI #23588: Pull request #14117 synchronize by Vithulep
53m 42s Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
53m 42s
ggml: aarch64: Implement SVE Kernels for Int 8 Quantization CI #23587: Pull request #14117 synchronize by Vithulep
13m 31s Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
13m 31s
ggml: aarch64: Implement SVE Kernels for Int 8 Quantization CI #23582: Pull request #14117 opened by Vithulep
30m 23s Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
Vithulep:Q8_0_SVE_implementaion_quantize_an_dequantize_function
30m 23s
vulkan: Better thread-safety for command pools/buffers CI #23581: Pull request #14116 synchronize by jeffbolznv
50m 14s jeffbolznv:commandpool_ctx
jeffbolznv:commandpool_ctx
50m 14s
vulkan: Better thread-safety for command pools/buffers CI #23578: Pull request #14116 opened by jeffbolznv
29m 19s jeffbolznv:commandpool_ctx
jeffbolznv:commandpool_ctx
29m 19s
[CANN]:Replace aclrtMemsetSync with InplaceZero operator for zero tensor creation CI #23577: Pull request #14002 synchronize by luyhcsu
7m 20s luyhcsu:dev/cann_backend
luyhcsu:dev/cann_backend
7m 20s
opencl: add mul_mv_id_q4_0_f32_8x_flat (#14003) CI #23576: Commit 4c763c8 pushed by max-krasnyansky
46m 56s master
master
46m 56s
Hybrid recurrent cache CI #23575: Pull request #13979 synchronize by gabe-l-hart
53m 22s gabe-l-hart:HybridRecurrentCache
gabe-l-hart:HybridRecurrentCache
53m 22s
Hybrid recurrent cache CI #23574: Pull request #13979 synchronize by gabe-l-hart
4m 37s gabe-l-hart:HybridRecurrentCache
gabe-l-hart:HybridRecurrentCache
4m 37s
Hybrid recurrent cache CI #23573: Pull request #13979 synchronize by gabe-l-hart
4m 54s gabe-l-hart:HybridRecurrentCache
gabe-l-hart:HybridRecurrentCache
4m 54s
kv-cache : avoid modifying recurrent cells when setting inputs (#13834) CI #23572: Commit dad5c44 pushed by compilade
49m 6s master
master
49m 6s
opencl: preliminary support for Q4_0 mul_mat_id using matvec CI #23570: Pull request #14003 synchronize by max-krasnyansky
54m 27s CodeLinaro:mul-mat-id
CodeLinaro:mul-mat-id
54m 27s
Hybrid recurrent cache CI #23564: Pull request #13979 synchronize by gabe-l-hart
54m 0s gabe-l-hart:HybridRecurrentCache
gabe-l-hart:HybridRecurrentCache
54m 0s
Hybrid recurrent cache CI #23563: Pull request #13979 synchronize by gabe-l-hart
11m 41s gabe-l-hart:HybridRecurrentCache
gabe-l-hart:HybridRecurrentCache
11m 41s
opencl: preliminary support for Q4_0 mul_mat_id using matvec CI #23562: Pull request #14003 synchronize by lhez
5m 38s CodeLinaro:mul-mat-id
CodeLinaro:mul-mat-id
5m 38s
vulkan: Track descriptor pools/sets per-context CI #23561: Pull request #14109 opened by jeffbolznv
1h 32m 31s jeffbolznv:descriptor_ctx2
jeffbolznv:descriptor_ctx2
1h 32m 31s
llama : support GEGLU for jina-bert-v2 (#14090) CI #23560: Commit 3678b83 pushed by CISC
1h 52m 10s master
master
1h 52m 10s
vulkan: force device 0 in CI (#14106) CI #23559: Commit 652b70e pushed by jeffbolznv
1h 37m 25s master
master
1h 37m 25s
ProTip! You can narrow down the results and go further in time using created:<2025-06-10 or the other filters available.