Skip to content

Actions: ngxson/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
549 workflow run results
549 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : fill usage info in embeddings and rerank responses (#10852) Server #737: Commit 05c3a44 pushed by ngxson
10m 0s master
master
10m 0s
server : (UI) fix missing async generator on safari (#10857) Server #736: Commit 227d7c5 pushed by ngxson
5m 0s master
master
5m 0s
vulkan: bugfixes for small subgroup size systems + llvmpipe test (#10… Server #735: Commit 7b1ec53 pushed by ngxson
5m 27s master
master
5m 27s
rwkv6: add wkv6 support for Vulkan backend (#10829) Server #734: Commit 160bc03 pushed by ngxson
8m 12s master
master
8m 12s
llama : add Deepseek MoE v1 & GigaChat models (#10827) Server #733: Commit a097415 pushed by ngxson
4m 29s master
master
4m 29s
server: (UI) add syntax highlighting and latex math rendering (#10808) Server #732: Commit 5478bbc pushed by ngxson
4m 57s master
master
4m 57s
server: Fix has_next_line in JSON response (#10818) Server #731: Commit 89d604f pushed by ngxson
5m 48s master
master
5m 48s
llama : add Qwen2VL support + multimodal RoPE (#10361) Server #730: Commit ba1cb19 pushed by ngxson
5m 11s master
master
5m 11s
Removes spurious \r in output that causes logging in journalctl to tr… Server #729: Commit 56eea07 pushed by ngxson
6m 14s master
master
6m 14s
Introducing experimental OpenCL backend with support for Qualcomm Adr… Server #728: Commit a76c56f pushed by ngxson
5m 50s master
master
5m 50s
Opt class for positional argument handling (#10508) Server #727: Commit c27ac67 pushed by ngxson
5m 11s master
master
5m 11s
Fix crash caused by ggml_backend_load_all when launching on Android A… Server #726: Commit 9f35e44 pushed by ngxson
5m 8s master
master
5m 8s
vulkan: small mul_mat_vec optimizations (#10665) Server #725: Commit 64ae065 pushed by ngxson
4m 43s master
master
4m 43s
SYCL: Reduce most of the compiler warnings (#10748) Server #724: Commit 83ed24a pushed by ngxson
5m 8s master
master
5m 8s
ggml : Fix compilation issues on ARM platform when building without f… Server #723: Commit d583cd0 pushed by ngxson
14m 52s master
master
14m 52s
common : improve -ctv -ctk CLI arguments (#10806) Server #722: Commit adffa6f pushed by ngxson
4m 32s master
master
4m 32s
CUDA: faster non-contiguous concat (#10760) Server #721: Commit 8faa1d4 pushed by ngxson
4m 24s master
master
4m 24s
common : add missing env var for speculative (#10801) Server #720: Commit 9fdb124 pushed by ngxson
10m 36s master
master
10m 36s
docs: update server streaming mode documentation (#9519) Server #719: Commit 5555c0c pushed by ngxson
5m 23s master
master
5m 23s
server : (UI) add tok/s, get rid of completion.js (#10786) Server #718: Commit 235f6e1 pushed by ngxson
5m 9s master
master
5m 9s
ci : pin nodejs to 22.11.0 (#10779) Server #717: Commit 92f77a6 pushed by ngxson
5m 10s master
master
5m 10s
docs: fix server documentation formatting (#10776) Server #716: Commit 4b4d92b pushed by ngxson
5m 18s master
master
5m 18s
ggml: load all backends from a user-provided search path (#10699) Server #715: Commit 43041d2 pushed by ngxson
4m 45s master
master
4m 45s
vulkan: request round-to-even for fp16 in im2col/rope_head (#10767) Server #714: Commit b685daf pushed by ngxson
4m 41s master
master
4m 41s
vulkan: dynamic subgroup size for the remaining k quants (#10745) Server #713: Commit dafae66 pushed by ngxson
5m 14s master
master
5m 14s
ProTip! You can narrow down the results and go further in time using created:<2024-12-10 or the other filters available.