Skip to content

Actions: am17an/llama.cpp

Actions

AI review (issues)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
ai-issues.yml
Workflows are not currently being run on this fork due to the scale of GitHub Actions usage. A repository maintainer can choose to re-enable these.
37 workflow runs
37 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
chat: Muse Glimmer silently ignores JSON schema constraints AI review (issues) #37: Issue #58 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: /infill ignores invalid prompt arrays and returns success AI review (issues) #36: Issue #57 opened by am17an
1d 0h 0m 8s
1d 0h 0m 8s
server: shell-completion and version options print initialization noise AI review (issues) #35: Issue #56 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: multi-choice completions report usage for only one choice AI review (issues) #34: Issue #55 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
cpu: AVX2 Q8_0 dot product flips signs for caller-supplied -128 AI review (issues) #33: Issue #54 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: RAM prompt cache is discarded after sleep and wake AI review (issues) #32: Issue #53 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
ggml: output flag changes reuse overlapping allocator storage AI review (issues) #31: Issue #52 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
jinja: unary minus before a variable fails to parse AI review (issues) #30: Issue #51 opened by am17an
1d 0h 0m 1s
1d 0h 0m 1s
server: Responses API rejects empty reasoning items AI review (issues) #29: Issue #50 opened by am17an
1d 0h 0m 11s
1d 0h 0m 11s
server: /v1/models returns boolean vocab_type instead of integer AI review (issues) #28: Issue #49 opened by am17an
1d 0h 0m 1s
1d 0h 0m 1s
server: CLI JSON schema rejects chat generation prefix AI review (issues) #27: Issue #48 opened by am17an
1d 0h 0m 1s
1d 0h 0m 1s
core: M-RoPE embedding batches overread null or one-plane positions AI review (issues) #26: Issue #47 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server router: CLI API key fails for chat when an API-key file is also used AI review (issues) #25: Issue #46 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
CUDA graphs: speculative decoding repeatedly resets warmup state AI review (issues) #24: Issue #45 opened by am17an
1d 0h 0m 7s
1d 0h 0m 7s
server router: queued model evicts the model serving its triggering request AI review (issues) #23: Issue #44 opened by am17an
1d 0h 0m 1s
1d 0h 0m 1s
server: malformed tool-call history returns HTTP 500 AI review (issues) #22: Issue #43 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: identical multimodal embeddings differ with default unified KV cache AI review (issues) #21: Issue #42 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: LFM2.5 MoE with DSpark aborts during CPU context init AI review (issues) #20: Issue #41 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: model-less preset spawns another router AI review (issues) #19: Issue #40 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: PEG until() accepts a missing final delimiter AI review (issues) #18: Issue #39 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: cached repeat changes deterministic Llama 3 output AI review (issues) #17: Issue #38 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: --batch-size 0 aborts in output_reserve AI review (issues) #16: Issue #37 opened by am17an
1d 0h 0m 2s
1d 0h 0m 2s
server: concurrent router loads can leave one model queued forever AI review (issues) #15: Issue #36 opened by am17an
1d 0h 0m 7s
1d 0h 0m 7s
server: streaming tools reject logprobs while n_probs works AI review (issues) #14: Issue #35 opened by am17an
1d 0h 0m 7s
1d 0h 0m 7s
server: id_slot pinned to an empty slot skips the prompt cache AI review (issues) #13: Issue #34 opened by am17an
1d 0h 0m 7s
1d 0h 0m 7s