Skip to content

Actions: teleprint-me/llama.cpp

Release

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
17 workflow runs
17 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

vulkan: optimize flash attention split_k_reduce (#14554)
Release #17: Commit 6efcd65 pushed by teleprint-me
July 9, 2025 01:10 1h 0m 13s master
July 9, 2025 01:10 1h 0m 13s
gguf-py : add support for chat template jinja files (#14508)
Release #16: Commit e75ba4c pushed by teleprint-me
July 2, 2025 19:28 56m 41s master
July 2, 2025 19:28 56m 41s
Add Conv2d for CPU (#14388)
Release #15: Commit 0a5a3b5 pushed by teleprint-me
June 30, 2025 18:03 55m 14s master
June 30, 2025 18:03 55m 14s
June 22, 2025 18:50 1h 1m 36s
sycl: Remove not needed copy f16->f32 for dnnl mul mat (#14125)
Release #13: Commit ed52f36 pushed by teleprint-me
June 13, 2025 00:03 1h 9m 57s master
June 13, 2025 00:03 1h 9m 57s
June 5, 2025 21:15 1h 14m 0s
June 2, 2025 16:58 17m 50s
gguf: fix failure on version == 0 (#13956)
Release #10: Commit 7675c55 pushed by teleprint-me
June 1, 2025 20:59 1h 12m 56s master
June 1, 2025 20:59 1h 12m 56s
CUDA: fix typo in FlashAttention code (#13926)
Release #9: Commit e562eec pushed by teleprint-me
May 30, 2025 20:00 32m 45s master
May 30, 2025 20:00 32m 45s
cmake: Guard GGML_CPU_ALL_VARIANTS by architecture (#13890)
Release #8: Commit ec9e030 pushed by teleprint-me
May 30, 2025 00:50 15m 15s master
May 30, 2025 00:50 15m 15s
May 29, 2025 07:35 17m 19s
llama : fix KV shift for qwen2vl (#13870)
Release #6: Commit 763d06e pushed by teleprint-me
May 28, 2025 21:19 1h 18m 57s master
May 28, 2025 21:19 1h 18m 57s
May 25, 2025 02:37 1h 16m 16s
ggml : fix the order of ggml_unary_op (#13718)
Release #4: Commit e16c473 pushed by teleprint-me
May 23, 2025 08:38 1h 3m 2s master
May 23, 2025 08:38 1h 3m 2s
May 21, 2025 02:23 30m 6s
kv-cache : add SWA support (#13194)
Release #2: Commit e298d2f pushed by teleprint-me
May 20, 2025 05:07 1h 5m 41s master
May 20, 2025 05:07 1h 5m 41s
minja: sync (qwen3) (#13573)
Release #1: Commit bc098c3 pushed by teleprint-me
May 16, 2025 05:51 1h 3m 48s master
May 16, 2025 05:51 1h 3m 48s