Skip to content

Actions: ggml-org/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
11,431 workflow runs
11,431 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

hip : fix warp mask width for rocWMMA compatibility Server #17379: Pull request #15239 opened by lhl
August 11, 2025 12:56 Action required lhl:rocm7-strixhalo-rocwmma-fix
lhl:rocm7-strixhalo-rocwmma-fix
August 11, 2025 12:56 Action required
server : allow specifying reasoning_format in HTTP request (#15238) Server #17378: Commit 53d0a12 pushed by ngxson
August 11, 2025 12:48 12m 23s master
master
August 11, 2025 12:48 12m 23s
CANN: Add broadcast for softmax and FA Server #17377: Pull request #15208 synchronize by hipudding
August 11, 2025 12:18 18m 38s hipudding:softmax
hipudding:softmax
August 11, 2025 12:18 18m 38s
server : allow specifying reasoning_format in HTTP request Server #17376: Pull request #15238 opened by ngxson
August 11, 2025 12:09 13m 3s xsn/fix_reasoning_format_webui
xsn/fix_reasoning_format_webui
August 11, 2025 12:09 13m 3s
common : add --override-tensor-draft, --cpu-moe-draft and --n-cpu-moe-draft parameters Server #17375: Pull request #15191 synchronize by Copilot AI
August 11, 2025 11:23 Action required copilot/vscode1754723901399
copilot/vscode1754723901399
August 11, 2025 11:23 Action required
kv-cache : fix seq_rm with seq_id == -1 (#15226) Server #17374: Commit 228f724 pushed by ggerganov
August 11, 2025 10:58 16m 46s master
master
August 11, 2025 10:58 16m 46s
model : gpt-oss simulate think tags when reasoning Server #17373: Pull request #15230 synchronize by aldehir
August 11, 2025 10:25 12m 31s aldehir:gpt-oss-quick-reasoning-fix
aldehir:gpt-oss-quick-reasoning-fix
August 11, 2025 10:25 12m 31s
model : gpt-oss simulate think tags when reasoning Server #17372: Pull request #15230 synchronize by aldehir
August 11, 2025 09:22 Action required aldehir:gpt-oss-quick-reasoning-fix
aldehir:gpt-oss-quick-reasoning-fix
August 11, 2025 09:22 Action required
kv-cache : log (debug) all streams in find_slot (#15176) Server #17371: Commit cd3069d pushed by danbev
August 11, 2025 09:21 46m 4s master
master
August 11, 2025 09:21 46m 4s
model : gpt-oss simulate think tags when reasoning Server #17370: Pull request #15230 opened by aldehir
August 11, 2025 08:58 35m 48s aldehir:gpt-oss-quick-reasoning-fix
aldehir:gpt-oss-quick-reasoning-fix
August 11, 2025 08:58 35m 48s
SvelteKit-based WebUI Server #17369: Pull request #14839 synchronize by allozaur
August 11, 2025 08:44 Action required allozaur:allozaur/svelte-webui
allozaur:allozaur/svelte-webui
August 11, 2025 08:44 Action required
kv-cache : fix seq_rm with seq_id == -1 Server #17368: Pull request #15226 synchronize by ggerganov
August 11, 2025 08:38 34m 50s gg/kv-cache-fix-seq-rm
gg/kv-cache-fix-seq-rm
August 11, 2025 08:38 34m 50s
gpt-oss: implement harmony parsing Server #17367: Pull request #15181 synchronize by aldehir
August 11, 2025 08:07 1h 12m 49s aldehir:feature/harmony-parser
aldehir:feature/harmony-parser
August 11, 2025 08:07 1h 12m 49s
kleidiai: fix unsigned overflow bug (#15150) Server #17366: Commit 002cb1b pushed by chaxu01
August 11, 2025 07:59 52m 29s master
master
August 11, 2025 07:59 52m 29s
server : implement /api/version endpoint for ollama compatibility (#15167 ) Server #17365: Pull request #15177 synchronize by albert-polak
August 11, 2025 07:52 Action required albert-polak:fix-ollama-version-error
albert-polak:fix-ollama-version-error
August 11, 2025 07:52 Action required
chat : Avoid partial reasoning tags in response content Server #17364: Pull request #15149 synchronize by p1-0tr
August 11, 2025 07:10 42m 49s p1-0tr:ps-fix-reasoning-tags-in-content
p1-0tr:ps-fix-reasoning-tags-in-content
August 11, 2025 07:10 42m 49s
kv-cache : fix seq_rm with seq_id == -1 Server #17363: Pull request #15226 opened by ggerganov
August 11, 2025 06:47 1h 13m 26s gg/kv-cache-fix-seq-rm
gg/kv-cache-fix-seq-rm
August 11, 2025 06:47 1h 13m 26s
CANN: Add broadcast for softmax and FA Server #17362: Pull request #15208 synchronize by hipudding
August 11, 2025 06:42 49m 42s hipudding:softmax
hipudding:softmax
August 11, 2025 06:42 49m 42s
CANN: Add broadcast for softmax and FA Server #17361: Pull request #15208 synchronize by hipudding
August 11, 2025 06:39 3m 6s hipudding:softmax
hipudding:softmax
August 11, 2025 06:39 3m 6s
CANN: Add broadcast for softmax and FA Server #17360: Pull request #15208 synchronize by hipudding
August 11, 2025 06:38 1m 36s hipudding:softmax
hipudding:softmax
August 11, 2025 06:38 1m 36s
CANN: Add broadcast for softmax and FA Server #17359: Pull request #15208 synchronize by hipudding
August 11, 2025 06:24 14m 14s hipudding:softmax
hipudding:softmax
August 11, 2025 06:24 14m 14s
CANN: Add broadcast for softmax and FA Server #17358: Pull request #15208 synchronize by hipudding
August 11, 2025 06:04 12m 44s hipudding:softmax
hipudding:softmax
August 11, 2025 06:04 12m 44s
server: implement GLM-style MTP Server #17357: Pull request #15225 opened by F1LM1
August 11, 2025 05:52 Action required F1LM1:glm4-moe-mtp
F1LM1:glm4-moe-mtp
August 11, 2025 05:52 Action required
gpt-oss: implement harmony parsing Server #17356: Pull request #15181 synchronize by aldehir
August 11, 2025 04:47 52m 28s aldehir:feature/harmony-parser
aldehir:feature/harmony-parser
August 11, 2025 04:47 52m 28s
ci : Fix -Werror=return-type in clip.cpp so ci/run.sh can run without issue Server #17355: Pull request #15221 opened by michaelgiba
August 11, 2025 01:52 12m 41s michaelgiba:fix-ci
michaelgiba:fix-ci
August 11, 2025 01:52 12m 41s