Skip to content

Actions: ggml-org/llama.cpp

Actions

Server (sanitize)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server-sanitize.yml
249 workflow runs
249 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

kv-cache : support attention rotation for heterogeneous iSWA (#21513) Server (sanitize) #249: Commit 4eb1951 pushed by ggerganov
3h 55m 20s master
master
3h 55m 20s
ggml-webgpu: parameterize submission size and add iOS specific limits… Server (sanitize) #248: Commit 957d717 pushed by ggerganov
3h 6m 53s master
master
3h 6m 53s
llama-server: fix model params not propagated (#21509) Server (sanitize) #247: Commit 69c28f1 pushed by taronaeo
5h 23m 23s master
master
5h 23m 23s
llama: remove per-arch tensor name lists (#21531) Server (sanitize) #246: Commit a8ec0df pushed by JohannesGaessler
3h 43m 5s master
master
3h 43m 5s
server : fix restore for checkpoints with pos_min == 0 (#21510) Server (sanitize) #245: Commit e8f5082 pushed by ggerganov
3h 20m 53s master
master
3h 20m 53s
ggml : deprecate GGML_OP_ADD1 (#21363) Server (sanitize) #244: Commit 22fc791 pushed by ggerganov
2h 16m 26s master
master
2h 16m 26s
ggml: Vulkan build, Linux -- output error string for errno on fork fa… Server (sanitize) #243: Commit 2a619f6 pushed by 0cc4m
2h 4m 15s master
master
2h 4m 15s
vulkan: add FA dequant for q4_1, q5_0, q5_1, iq4_nl (#21029) Server (sanitize) #242: Commit edd4d9b pushed by 0cc4m
1h 48m 18s master
master
1h 48m 18s
webui : store reasoning_content so it is sent back in subsequent requ… Server (sanitize) #241: Commit 482192f pushed by allozaur
20m 47s master
master
20m 47s
fix: Detect streaming state in reasoning content blocks (#21549) Server (sanitize) #240: Commit ecce008 pushed by allozaur
21m 6s master
master
21m 6s
Fix rtl text rendering (#21382) Server (sanitize) #239: Commit d1f82e3 pushed by ServeurpersoCom
23m 33s master
master
23m 33s
[SYCL] Add Q8_0 reorder optimization (~3x tg speedup on Intel Arc) (#… Server (sanitize) #238: Commit 0988acc pushed by arthw
58m 14s master
master
58m 14s
ggml-webgpu: Add the support of MUL_MAT_ID (#21147) Server (sanitize) #237: Commit d0a6dfe pushed by reeselevine
1h 47m 58s master
master
1h 47m 58s
ggml: add Q1_0 1-bit quantization support (CPU) (#21273) Server (sanitize) #236: Commit 2e1f0a8 pushed by pwilkin
2h 32m 15s master
master
2h 32m 15s
cli: fix stripping of \n in multiline input (#21485) Server (sanitize) #235: Commit 506200c pushed by pwilkin
1h 3m 21s master
master
1h 3m 21s
llama-bench: add -fitc and -fitt to arguments (#21304) Server (sanitize) #234: Commit 94ca829 pushed by am17an
2h 46m 25s master
master
2h 46m 25s
vocab : add byte token handling to BPE detokenizer for Gemma4 (#21488) Server (sanitize) #233: Commit 4aa962e pushed by aldehir
2h 18m 14s master
master
2h 18m 14s
server : handle unsuccessful sink.write in chunked stream provider (#… Server (sanitize) #232: Commit 482d862 pushed by ngxson
45m 42s master
master
45m 42s
convert : set "add bos" == True for Gemma 4 (#21500) Server (sanitize) #231: Commit 400ac8e pushed by ggerganov
17m 15s master
master
17m 15s
sycl : handle other FA case (#21377) Server (sanitize) #230: Commit f51fd36 pushed by ggerganov
2m 9s master
master
2m 9s
hexagon: slight optimization for argosrt output init (#21463) Server (sanitize) #229: Commit 25eec6f pushed by max-krasnyansky
40m 47s master
master
40m 47s
llama : correct platform-independent loading of BOOL metadata (#21428) Server (sanitize) #228: Commit 58190cc pushed by CISC
1h 2m 44s master
master
1h 2m 44s
model : add HunyuanOCR support (#21395) Server (sanitize) #227: Commit af76639 pushed by ngxson
41m 57s master
master
41m 57s
server : fix logging of build + system info (#21460) Server (sanitize) #226: Commit 5d3a4a7 pushed by ngxson
21m 46s master
master
21m 46s
server: Fix undefined timing measurement errors in server context (#2… Server (sanitize) #225: Commit 9c69907 pushed by taronaeo
21m 36s master
master
21m 36s