Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
3,825 workflow run results
3,825 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19300: Pull request #11213 synchronize by ggerganov
35m 0s gg/llama-kv-cache
gg/llama-kv-cache
35m 0s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19299: Pull request #11213 synchronize by ggerganov
14m 23s gg/llama-kv-cache
gg/llama-kv-cache
14m 23s
vulkan: use kompute matmul shaders on embedded GPUs CI #19298: Pull request #11525 synchronize by slp
33m 10s slp:vulkan-embedded
slp:vulkan-embedded
33m 10s
sync: minja (https://github.com/google/minja/commit/a72057e5190de2c61… CI #19296: Commit d7b31a9 pushed by ochafik
38m 22s master
master
38m 22s
server : use common_token_to_piece instead of common_detokenize CI #19295: Pull request #11740 synchronize by danbev
33m 34s danbev:server-logprobs-11728
danbev:server-logprobs-11728
33m 34s
server : use common_token_to_piece instead of common_detokenize CI #19294: Pull request #11740 synchronize by danbev
20m 20s danbev:server-logprobs-11728
danbev:server-logprobs-11728
20m 20s
server : use common_token_to_piece instead of common_detokenize CI #19293: Pull request #11740 synchronize by danbev
4m 25s danbev:server-logprobs-11728
danbev:server-logprobs-11728
4m 25s
ggml: move kvalues_iq4nl definition to ggml-common.h CI #19292: Pull request #11785 opened by HungMingWu
40m 7s HungMingWu:kvalues_iq4nl
HungMingWu:kvalues_iq4nl
40m 7s
vulkan: Make Vulkan optional at runtime (#11493). (#11494) CI #19291: Commit c2a67ef pushed by 0cc4m
46m 28s master
master
46m 28s
vulkan: add environment variable GGML_VK_PREFER_HOST_MEMORY to avoid … CI #19290: Commit b044a0f pushed by 0cc4m
43m 32s master
master
43m 32s
llama: Add support for RWKV v7 architecture CI #19289: Pull request #11452 synchronize by MollySophia
43m 46s MollySophia:rwkv-v7
MollySophia:rwkv-v7
43m 46s
llama: Add support for RWKV v7 architecture CI #19288: Pull request #11452 synchronize by MollySophia
6m 10s MollySophia:rwkv-v7
MollySophia:rwkv-v7
6m 10s
chore: update ggml-cpu-aarch64.cpp CI #19287: Pull request #11782 opened by eltociear
28m 34s eltociear:patch-12
eltociear:patch-12
28m 34s
fix crash on non-AVX systems dynamically loading GGML CPU backends CI #19285: Pull request #11780 opened by jmorganca
29m 13s jmorganca:jmorganca/sgemm-initialization
jmorganca:jmorganca/sgemm-initialization
29m 13s
vulkan: improve im2col performance CI #19284: Pull request #11778 synchronize by daniandtheweb
28m 7s daniandtheweb:vk-shader-optimizations-1
daniandtheweb:vk-shader-optimizations-1
28m 7s
vulkan: improve im2col performance CI #19283: Pull request #11778 opened by daniandtheweb
3m 45s daniandtheweb:vk-shader-optimizations-1
daniandtheweb:vk-shader-optimizations-1
3m 45s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19282: Pull request #11607 synchronize by ochafik
28m 58s ochafik:r1-toolcall
ochafik:r1-toolcall
28m 58s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19281: Pull request #11607 synchronize by ochafik
33m 1s ochafik:r1-toolcall
ochafik:r1-toolcall
33m 1s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19279: Pull request #11607 synchronize by ochafik
30m 50s ochafik:r1-toolcall
ochafik:r1-toolcall
30m 50s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19277: Pull request #11607 synchronize by ochafik
34m 39s ochafik:r1-toolcall
ochafik:r1-toolcall
34m 39s
CUDA: use arch list for compatibility check CI #19276: Pull request #11775 opened by JohannesGaessler
34m 2s JohannesGaessler:cuda-fix-pascal-mmv
JohannesGaessler:cuda-fix-pascal-mmv
34m 2s
sync: minja CI #19275: Pull request #11774 opened by ochafik
29m 17s ochafik:sync-minja-5
ochafik:sync-minja-5
29m 17s
ggml : fix more imatrix nan cases CI #19274: Pull request #11773 opened by slaren
31m 24s sl/more-imatrix-nan-fixes
sl/more-imatrix-nan-fixes
31m 24s
imatrix : use GGUF to store importance matrices CI #19273: Pull request #9400 synchronize by compilade
33m 11s compilade/imatrix-batched-chunks
compilade/imatrix-batched-chunks
33m 11s
ggml-cpu : add chunking support to mul_mat_id CI #19272: Pull request #11666 synchronize by slaren
30m 35s sl/mmid-cpu-perf
sl/mmid-cpu-perf
30m 35s