Skip to content

Actions: ggml-org/llama.cpp

Actions

Release

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
release.yml
1,476 workflow runs
1,476 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

clip: fix nb calculation for qwen3-vl (#17594) Release #1480: Commit 7f8ef50 pushed by ngxson
2h 39m 47s master
master
2h 39m 47s
cli: add migration warning (#17620) Release #1479: Commit 3c136b2 pushed by ngxson
2h 3m 6s master
master
2h 3m 6s
common : throttle download progress output to reduce IO flush (#17427) Release #1478: Commit beb1f0c pushed by ggerganov
1h 42m 41s master
master
1h 42m 41s
common: add LLAMA_LOG_FILE env var (#17609) Release #1477: Commit def5404 pushed by ngxson
1h 32m 40s master
master
1h 32m 40s
ggml: fix: macOS build with -DGGML_BACKEND_DL=ON (#17581) Release #1476: Commit fa04659 pushed by taronaeo
53m 38s master
master
53m 38s
common: update env var name (#17588) Release #1475: Commit 5a6241f pushed by taronaeo
49m 28s master
master
49m 28s
CUDA: add stream-based concurrency (#16991) Release #1474: Commit c7af376 pushed by am17an
2h 11m 7s master
master
2h 11m 7s
cuda : add error checking for cudaMemcpyAsync in argsort (#17599) Release #1473: Commit 00425e2 pushed by am17an
1h 21m 59s master
master
1h 21m 59s
vulkan : fix FA mask load with bounds check (coopmat2) (#17606) Release #1472: Commit 385c3da pushed by pwilkin
1h 22m 55s master
master
1h 22m 55s
server: move server-context to its own cpp|h (#17595) Release #1471: Commit ab49f09 pushed by ngxson
37m 36s master
master
37m 36s
server: explicitly set the function name in lambda (#17538) Release #1470: Commit 8c32d9d pushed by ngxson
55m 4s master
master
55m 4s
common : fix json schema with '\' in literals (#17307) Release #1469: Commit 0874693 pushed by CISC
52m 33s master
master
52m 33s
sycl : support to malloc memory on device more than 4GB, update the d… Release #1464: Commit 7d2add5 pushed by ggerganov
1h 28m 49s master
master
1h 28m 49s
ggml: replace hwcap with riscv_hwprobe for RVV detection (#17567) Release #1463: Commit f698a79 pushed by ggerganov
1h 28m 12s master
master
1h 28m 12s
Vulkan: MMVQ Integer Dot K-Quant and MUL_MAT_ID support (#16900) Release #1462: Commit 47a268e pushed by 0cc4m
24m 45s master
master
24m 45s
vulkan: improve topk perf for large k, fix overflow in unit tests (#1… Release #1461: Commit 59d8d4e pushed by 0cc4m
52m 11s master
master
52m 11s
common : move all common_chat_parse_* to chat-parser.cpp. (#17481) Release #1460: Commit 03914c7 pushed by ngxson
1h 52m 26s master
master
1h 52m 26s
server: fix: /metrics endpoint returning JSON-escaped Prometheus form… Release #1459: Commit 3ce7a65 pushed by ngxson
1h 44m 59s master
master
1h 44m 59s
ggml : add GGML_SCHED_NO_REALLOC option to disable reallocations in g… Release #1458: Commit e072b20 pushed by ggerganov
3h 7m 14s master
master
3h 7m 14s
[MUSA] enable fp16/fast_fp16/bf16_mma on PH1 (#17551) Release #1457: Commit c6f7a42 pushed by JohannesGaessler
4h 34m 32s master
master
4h 34m 32s
ggml-cuda: add stricter checking for fusion (#17568) Release #1456: Commit 2e7ef98 pushed by am17an
2h 45m 41s master
master
2h 45m 41s
server : add Anthropic Messages API support (#17570) Release #1455: Commit ddf9f94 pushed by ngxson
2h 13m 38s master
master
2h 13m 38s
model : Qwen3 Next (#16095) Release #1454: Commit ff55414 pushed by CISC
1h 35m 8s master
master
1h 35m 8s
CUDA: no FP16 arithmetic for vector FA kernel (#17558) Release #1453: Commit 73955f7 pushed by JohannesGaessler
2h 43m 18s master
master
2h 43m 18s
vulkan: Implement GGML_OP_TRI (#17503) Release #1452: Commit 35cf888 pushed by 0cc4m
2h 23m 24s master
master
2h 23m 24s