Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
3,459 workflow run results
3,459 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml-cpu : add chunking support to mul_mat_id CI #19158: Pull request #11666 synchronize by slaren
31m 10s sl/mmid-cpu-perf
sl/mmid-cpu-perf
31m 10s
ggml-cpu : add chunking support to mul_mat_id CI #19157: Pull request #11666 synchronize by slaren
3m 8s sl/mmid-cpu-perf
sl/mmid-cpu-perf
3m 8s
ggml-cpu : add chunking support to mul_mat_id CI #19156: Pull request #11666 synchronize by slaren
4m 27s sl/mmid-cpu-perf
sl/mmid-cpu-perf
4m 27s
vulkan: use smaller combined allocations to avoid fragmentation CI #19155: Pull request #11551 synchronize by jeffbolznv
34m 28s jeffbolznv:smaller_allocations
jeffbolznv:smaller_allocations
34m 28s
common : add default embeddings presets CI #19154: Pull request #11677 opened by danbev
41m 15s danbev:embeddings-presets
danbev:embeddings-presets
41m 15s
ggml-cpu: Add CPU backend support for KleidiAI library CI #19153: Pull request #11390 synchronize by chaxu01
38m 11s chaxu01:feature/kleidiai-cpu-backend
chaxu01:feature/kleidiai-cpu-backend
38m 11s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19152: Pull request #11607 synchronize by ochafik
57m 21s ochafik:r1-toolcall
ochafik:r1-toolcall
57m 21s
tool-call: add support for tool-calls using Model Context Protocol CI #19151: Pull request #11556 synchronize by bandoti
1h 1m 37s bandoti:llamacli-tools
bandoti:llamacli-tools
1h 1m 37s
SYCL: Adjust support condition for norm operators CI #19150: Pull request #11674 opened by qnixsynapse
49m 47s qnixsynapse:patch-2
qnixsynapse:patch-2
49m 47s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19149: Pull request #11607 synchronize by ochafik
29m 52s ochafik:r1-toolcall
ochafik:r1-toolcall
29m 52s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19148: Pull request #11607 synchronize by ochafik
18m 1s ochafik:r1-toolcall
ochafik:r1-toolcall
18m 1s
metal : adjust support conditions for norm operators (#11671) CI #19147: Commit d774ab3 pushed by ggerganov
40m 57s master
master
40m 57s
metal : adjust support conditions for norm operators CI #19146: Pull request #11671 opened by ggerganov
1h 11m 35s gg/metal-norm-conds
gg/metal-norm-conds
1h 11m 35s
SYCL: Kernel function refactor CI #19145: Pull request #11515 synchronize by qnixsynapse
1h 1m 1s qnixsynapse:refactor_kernels
qnixsynapse:refactor_kernels
1h 1m 1s
CUDA: support for mat. mul. with ne03 != ne13 (#11656) CI #19144: Commit fa62da9 pushed by JohannesGaessler
1h 1m 50s master
master
1h 1m 50s
llava: add quantization for the visual projector LLAVA, Qwen2VL (#11644) CI #19143: Commit 1ec2080 pushed by monatis
1h 15m 56s master
master
1h 15m 56s
Added quantization for the visual projector LLAVA, Qwen2VL CI #19142: Pull request #11644 synchronize by samkoesnadi
31m 40s samkoesnadi:feat/clip-quantize
samkoesnadi:feat/clip-quantize
31m 40s
Added quantization for the visual projector LLAVA, Qwen2VL CI #19141: Pull request #11644 synchronize by samkoesnadi
10m 28s samkoesnadi:feat/clip-quantize
samkoesnadi:feat/clip-quantize
10m 28s
llama: fix (non hf) glm4 models CI #19140: Pull request #11670 opened by tv1wnd
6m 4s tv1wnd:old-glm4-fix
tv1wnd:old-glm4-fix
6m 4s
llama : rename batch.logits to batch.output CI #19139: Pull request #10004 synchronize by danbev
35m 42s danbev:rename-logits-output
danbev:rename-logits-output
35m 42s
fix bug in minicpm-v code CI #19138: Pull request #11513 synchronize by tc-mb
33m 1s tc-mb:fix-bug-in-minicpm-v-code
tc-mb:fix-bug-in-minicpm-v-code
33m 1s
SYCL: Kernel function refactor CI #19137: Pull request #11515 synchronize by qnixsynapse
27m 58s qnixsynapse:refactor_kernels
qnixsynapse:refactor_kernels
27m 58s
ggml-cpu : add chunking support to mul_mat_id CI #19136: Pull request #11666 opened by slaren
28m 56s sl/mmid-cpu-perf
sl/mmid-cpu-perf
28m 56s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19135: Pull request #11607 synchronize by ochafik
40m 21s ochafik:r1-toolcall
ochafik:r1-toolcall
40m 21s
sync: minja (#11641) CI #19134: Commit 9f4cc8f pushed by ochafik
38m 7s master
master
38m 7s