Skip to content

Actions: CodeLinaro/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
19 workflow runs
19 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
gguf-py : add support for endian conversion of BF16 data (#16594) Server #245: Commit 7adc79c pushed by shawngu-quic
44m 11s master
master
44m 11s
metal : add opt_step_adamw and op_sum (#16529) Server #244: Commit a31cf36 pushed by max-krasnyansky
37m 28s master
master
37m 28s
webui: updated the chat service to only include max_tokens in the req… Server #243: Commit 1faa13a pushed by max-krasnyansky
35m 34s master
master
35m 34s
server : fix cancel pending task (#16467) Server #242: Commit d2ee056 pushed by max-krasnyansky
30m 42s master
master
30m 42s
llama : add --no-host to disable host buffers (#16310) Server #241: Commit 3df2244 pushed by max-krasnyansky
38m 30s master
master
38m 30s
CI: reenable cdna in rocm docker builds (#16376) Server #240: Commit c8dedc9 pushed by shawngu-quic
34m 15s master
master
34m 15s
ci: Properly install rocwmma for hip builds (#16305) Server #239: Commit 1fe4e38 pushed by max-krasnyansky
36m 18s master
master
36m 18s
ggml : implement set_rows with i32 index (#16159) Server #238: Commit 3ecb2f6 pushed by lhez
35m 47s master
master
35m 47s
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorr… Server #237: Commit 40be511 pushed by lhez
14m 11s master
master
14m 11s
ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (#15797) Server #236: Commit 360d653 pushed by lhez
13m 26s master
master
13m 26s
json : support enum values within allOf (#15830) Server #235: Commit 7057faf pushed by lhez
15m 1s master
master
15m 1s
CUDA: Accelerate MXFP4 table lookup using __byte_perm (#15451) Server #234: Commit 74f52f7 pushed by max-krasnyansky
13m 4s master
master
13m 4s
llama : add 18-layer model type for Gemma 3-270m (#15319) Server #233: Commit 7a0de96 pushed by max-krasnyansky
11m 44s master
master
11m 44s
HIP: disable sync warp shuffel operators from clr amd_warp_sync_funct… Server #232: Commit b049315 pushed by max-krasnyansky
15m 26s master
master
15m 26s
embeddings: fix extraction of CLS pooling results (#14927) Server #231: Commit a118d80 pushed by lhez
11m 43s master
master
11m 43s
ci : disable fast-math for Metal GHA CI (#14478) Server #230: Commit de56944 pushed by lhez
11m 51s master
master
11m 51s
batch : fix check for empty sequences in memory (#14364) Server #229: Commit 62af464 pushed by lhez
10m 38s master
master
10m 38s
cmake: remove shader-gen step-targets from ggml-vulkan (#14226) Server #228: Commit c465030 pushed by lhez
10m 16s master
master
10m 16s
common : suggest --jinja when autodetection fails (#14222) Server #227: Commit e434e69 pushed by lhez
11m 6s master
master
11m 6s