Skip to content

Actions: ggml-org/llama.cpp

Actions

CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build.yml
3,579 workflow run results
3,579 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

ggml : fix LoongArch compile error with 128-bit SIMD (#11701) CI #19187: Commit 8d4d2be pushed by ggerganov
31m 41s master
master
31m 41s
llama : refactor llama_kv_cache, llama_context and llm_build_context CI #19186: Pull request #11213 synchronize by ggerganov
1h 10m 53s gg/llama-kv-cache
gg/llama-kv-cache
1h 10m 53s
When llama_chat_apply_template doesn't work CI #19185: Pull request #11687 synchronize by ericcurtin
1h 2m 49s fall-back-to-jinja
fall-back-to-jinja
1h 2m 49s
Fix LoongArch compile error with 128-bit SIMD CI #19184: Pull request #11701 opened by junchao-loongson
58m 55s junchao-loongson:master
junchao-loongson:master
58m 55s
fix bug in minicpm-v code CI #19183: Pull request #11513 synchronize by tc-mb
1h 5m 6s tc-mb:fix-bug-in-minicpm-v-code
tc-mb:fix-bug-in-minicpm-v-code
1h 5m 6s
llama : add log about loading model tensors CI #19182: Pull request #11699 opened by ggerganov
31m 10s gg/llama-add-log
gg/llama-add-log
31m 10s
llama : rename batch.logits to batch.output CI #19181: Pull request #10004 synchronize by danbev
37m 26s danbev:rename-logits-output
danbev:rename-logits-output
37m 26s
vulkan: optimize coopmat2 iq2/iq3 callbacks (#11521) CI #19180: Commit 2c6c8df pushed by 0cc4m
47m 13s master
master
47m 13s
vulkan: initial support for IQ4_XS quantization (#11501) CI #19179: Commit 8a7e3bf pushed by 0cc4m
47m 4s master
master
47m 4s
vulkan: use smaller combined allocations to avoid fragmentation (#11551) CI #19178: Commit 1b598b3 pushed by 0cc4m
36m 2s master
master
36m 2s
metal : avoid breaking build when metal API predates TARGET_OS_VISION… CI #19174: Commit 902368a pushed by jhen0409
33m 58s master
master
33m 58s
llama : add option to override model tensor buffers CI #19173: Pull request #11397 synchronize by slaren
43m 34s sl/custom-tensor-offload
sl/custom-tensor-offload
43m 34s
When llama_chat_apply_template doesn't work CI #19172: Pull request #11687 synchronize by ericcurtin
16m 24s fall-back-to-jinja
fall-back-to-jinja
16m 24s
When llama_chat_apply_template doesn't work CI #19171: Pull request #11687 synchronize by ericcurtin
26s fall-back-to-jinja
fall-back-to-jinja
26s
metal : avoid breaking build when metal API predates TARGET_OS_VISION CI #19170: Pull request #11690 opened by charles-dyfis-net
41m 52s charles-dyfis-net:fix-metalkit-without-vision-build
charles-dyfis-net:fix-metalkit-without-vision-build
41m 52s
When llama_chat_apply_template doesn't work CI #19169: Pull request #11687 synchronize by ericcurtin
35m 18s fall-back-to-jinja
fall-back-to-jinja
35m 18s
When llama_chat_apply_template doesn't work CI #19168: Pull request #11687 synchronize by ericcurtin
10m 4s fall-back-to-jinja
fall-back-to-jinja
10m 4s
When llama_chat_apply_template doesn't work CI #19167: Pull request #11687 opened by ericcurtin
5m 11s fall-back-to-jinja
fall-back-to-jinja
5m 11s
ggml-cpu : add chunking support to mul_mat_id CI #19165: Pull request #11666 synchronize by slaren
30m 40s sl/mmid-cpu-perf
sl/mmid-cpu-perf
30m 40s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19164: Pull request #11607 synchronize by ochafik
27m 38s ochafik:r1-toolcall
ochafik:r1-toolcall
27m 38s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19163: Pull request #11607 synchronize by ochafik
13m 56s ochafik:r1-toolcall
ochafik:r1-toolcall
13m 56s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19162: Pull request #11607 synchronize by ochafik
5m 16s ochafik:r1-toolcall
ochafik:r1-toolcall
5m 16s
tool-call: add support for tool-calls using Model Context Protocol CI #19161: Pull request #11556 synchronize by bandoti
38m 1s bandoti:llamacli-tools
bandoti:llamacli-tools
38m 1s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19160: Pull request #11607 synchronize by ochafik
21m 53s ochafik:r1-toolcall
ochafik:r1-toolcall
21m 53s
server: fix tool-call of DeepSeek R1 Qwen, return reasoning_content (Command 7RB & DeepSeek R1) unless --reasoning-format none CI #19159: Pull request #11607 synchronize by ochafik
6m 42s ochafik:r1-toolcall
ochafik:r1-toolcall
6m 42s
ProTip! You can narrow down the results and go further in time using created:<2025-02-05 or the other filters available.