Skip to content

Actions: huggingface/AnyLanguageModel

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
507 workflow runs
507 workflow runs

Filter by Workflow

⌥ + click/return to exclude

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
Remove calls to the deprecated llama_set_warmup (#205) CI #474: Commit 6fd35ce pushed by mattt
2m 52s main
main
2m 52s
Add tool calling to LlamaLanguageModel, including streaming CI #473: Pull request #216 opened by james-333i
Action required james-333i:feat/llama-tool-calling
james-333i:feat/llama-tool-calling
Action required
Reuse a per-session context across chat exchanges CI #472: Pull request #215 opened by james-333i
Action required james-333i:feat/llama-session-context
james-333i:feat/llama-session-context
Action required
Render the Gemma 4 chat format when template detection fails CI #471: Pull request #214 opened by james-333i
Action required james-333i:fix/llama-gemma4-template
james-333i:fix/llama-gemma4-template
Action required
Add vision support to LlamaLanguageModel via mtmd CI #470: Pull request #213 opened by james-333i
Action required james-333i:feat/llama-vision
james-333i:feat/llama-vision
Action required
Widen the empty-array probe to merged item-start tokens CI #469: Pull request #212 opened by james-333i
Action required james-333i:fix/structured-empty-array-probe
james-333i:fix/structured-empty-array-probe
Action required
Adopt Foundation Models OS 27 surfaces: image attachments, capabilities, context size CI #468: Pull request #206 synchronize by james-333i
Action required james-333i:feat/foundation-models-os27
james-333i:feat/foundation-models-os27
Action required
Deliver streamed tokens live instead of after generation completes CI #467: Pull request #195 synchronize by james-333i
Action required james-333i:fix/llama-token-streaming
james-333i:fix/llama-token-streaming
Action required
Route think and keep_alive to the top level of Ollama chat requests CI #466: Pull request #200 synchronize by james-333i
-1s james-333i:fix/152-ollama-think
james-333i:fix/152-ollama-think
-1s
Remove calls to the deprecated llama_set_warmup CI #465: Pull request #205 synchronize by james-333i
3h 37m 44s james-333i:fix/llama-warmup-removal
james-333i:fix/llama-warmup-removal
3h 37m 44s
Expands support for Anthropic thinking & Adds support for effort. CI #464: Pull request #211 opened by ActuallyTaylor
-1s ActuallyTaylor:anthropic-thinking-effort
ActuallyTaylor:anthropic-thinking-effort
-1s
Add an assistant prefill option to LlamaLanguageModel (#198) CI #463: Commit 4bd6de2 pushed by mattt
9m 55s main
main
9m 55s
Add an assistant prefill option to LlamaLanguageModel CI #462: Pull request #198 synchronize by mattt
20s james-333i:feat/llama-assistant-prefill
james-333i:feat/llama-assistant-prefill
20s
Add Swift 6.3 to CI (#209) CI #461: Commit 9db43f6 pushed by mattt
11m 23s main
main
11m 23s
Fix constrained sampling ignoring the allowed-token set (#197) CI #460: Commit 9f89ec8 pushed by mattt
4m 45s main
main
4m 45s
Bump actions/checkout from 7.0.0 to 7.0.1 in the actions group across 1 directory CI #459: Pull request #179 synchronize by dependabot Bot
2m 23s dependabot/github_actions/actions-7a5a078ad4
dependabot/github_actions/actions-7a5a078ad4
2m 23s
Enable Metal GPU offload for llama.cpp models by default (#194) CI #458: Commit 8055192 pushed by mattt
2m 34s main
main
2m 34s
github_actions in / for actions/checkout - Update #1552211374 Dependabot Updates #5: by dependabot Bot
41s main
main
41s
Fix three places where constrained JSON generation ignores the model … CI #457: Commit 044dd48 pushed by mattt
2m 7s main
main
2m 7s
Add Swift 6.3 to CI CI #456: Pull request #209 opened by mattt
9m 27s add-swift-6.3-ci
add-swift-6.3-ci
9m 27s
Raise the macOS CI job timeout to 20 minutes (#208) CI #455: Commit d61f579 pushed by mattt
7m 48s main
main
7m 48s
Ingest decoder prompts in batch-sized chunks (#196) CI #454: Commit 562b034 pushed by mattt
8m 24s main
main
8m 24s
Adopt the MLX Memory API (#204) CI #453: Commit 7d12b28 pushed by mattt
10m 3s main
main
10m 3s
Cancel the generation when a response stream's consumer stops early (… CI #452: Commit 4f50aeb pushed by mattt
8m 56s main
main
8m 56s
Accept stringified primitives in Generable conversions (#201) CI #451: Commit 0ae270c pushed by mattt
7m 47s main
main
7m 47s