Skip to content

Actions: srogmann/llama.cpp

Actions

Release

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
release.yml
63 workflow runs
63 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
cmake : remove STATIC from impl libraries, enable LLAMA_BUILD_APP by … Release #63: Commit bb28c1f pushed by srogmann
1d 0h 0m 3s master
master
1d 0h 0m 3s
hexagon: enable support for NORM op (#23319) Release #62: Commit ac76808 pushed by srogmann
1d 0h 0m 3s master
master
1d 0h 0m 3s
cmake : do not install conversion script (#23204) Release #61: Commit e0de4c2 pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
Ggml/cuda snake fusion hardening (#22912) Release #60: Commit e936660 pushed by srogmann
1d 0h 0m 5s master
master
1d 0h 0m 5s
cmake : update BoringSSL to 0.20260508.0 (#22839) Release #59: Commit 5757c4d pushed by srogmann
1d 0h 0m 1s master
master
1d 0h 0m 1s
common : check for null getpwuid in hf-cache (#22550) Release #58: Commit beb42ff pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
common : do not pass prompt tokens to reasoning budget sampler (#22488) Release #57: Commit d775992 pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
server : convert_anthropic_to_oai: also copy chat_template_kwargs (#2… Release #56: Commit 185cbff pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
spec : reset i_last when low acceptance streak occurs (#22168) Release #55: Commit 72d693e pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
server : remove /api endpoints (#22165) Release #54: Commit cf8b0db pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
ci : install spirv-headers for vulkan-cross (#22109) Release #53: Commit 037bfe3 pushed by srogmann
1d 0h 0m 1s master
master
1d 0h 0m 1s
codeowners: add team member comments (#21714) Release #52: Commit b572d1e pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
fix: free ctx_copy in ggml_opt_free to plug per-training-session leak… Release #51: Commit 2dcb7f7 pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
docker : bump cuda12 to 12.9.1 (#20920) Release #50: Commit 277ff5f pushed by srogmann
1d 0h 0m 3s master
master
1d 0h 0m 3s
fix: tool call parsing for LFM2 and LFM2.5 models (#21242) Release #49: Commit 1d6d4cf pushed by srogmann
1d 0h 0m 3s master
master
1d 0h 0m 3s
ai : limit runtime of the agent (#20816) Release #48: Commit 4cb7e0b pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
metal : add FA specialization for HSK = 320, HSV = 256 (#20549) Release #47: Commit b30a5fd pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
llama-quant : correct n_attention_wv usage (#20357) Release #46: Commit 10e5b14 pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
ggml : bump RPC version (#20330) Release #45: Commit 90b2731 pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
server : do not create checkpoints right after mtmd chunks (#20232) Release #44: Commit d417bc4 pushed by srogmann
1d 0h 0m 1s master
master
1d 0h 0m 1s
ggml webgpu: Clean up per-thread parameter buffer pool and job submis… Release #43: Commit 4d828bd pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s
vulkan: fix fp16 Flash Attention on Windows AMD RDNA2 and below (#19921) Release #42: Commit 723c710 pushed by srogmann
1d 0h 0m 6s master
master
1d 0h 0m 6s
ggml/gguf : prevent integer overflows (#19856) Release #41: Commit 418dea3 pushed by srogmann
1d 0h 0m 3s master
master
1d 0h 0m 3s
perplexity: add proper batching (#19661) Release #40: Commit d612901 pushed by srogmann
1d 0h 0m 1s master
master
1d 0h 0m 1s
chat: fix case where template accepts type content only (#19419) Release #39: Commit 98e57ca pushed by srogmann
1d 0h 0m 2s master
master
1d 0h 0m 2s