Skip to content

Actions: huggingface/AnyLanguageModel

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
472 workflow runs
472 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
Cancel the generation when a response stream's consumer stops early CI #442: Pull request #202 opened by james-333i
Action required james-333i:fix/stream-consumer-cancellation
james-333i:fix/stream-consumer-cancellation
Action required
Accept stringified primitives in Generable conversions CI #441: Pull request #201 opened by james-333i
Action required james-333i:fix/tool-argument-string-coercion
james-333i:fix/tool-argument-string-coercion
Action required
Route think and keep_alive to the top level of Ollama chat requests CI #440: Pull request #200 opened by james-333i
Action required james-333i:fix/152-ollama-think
james-333i:fix/152-ollama-think
Action required
Send images per message in Ollama chat requests CI #439: Pull request #199 opened by james-333i
Action required james-333i:fix/167-ollama-vision-images
james-333i:fix/167-ollama-vision-images
Action required
Add an assistant prefill option to LlamaLanguageModel CI #438: Pull request #198 opened by james-333i
Action required james-333i:feat/llama-assistant-prefill
james-333i:feat/llama-assistant-prefill
Action required
Fix constrained sampling ignoring the allowed-token set CI #437: Pull request #197 opened by james-333i
Action required james-333i:fix/llama-constrained-sampling
james-333i:fix/llama-constrained-sampling
Action required
Ingest decoder prompts in batch-sized chunks CI #436: Pull request #196 opened by james-333i
Action required james-333i:fix/llama-chunked-prompt
james-333i:fix/llama-chunked-prompt
Action required
Deliver streamed tokens live instead of after generation completes CI #435: Pull request #195 opened by james-333i
Action required james-333i:fix/llama-token-streaming
james-333i:fix/llama-token-streaming
Action required
Enable Metal GPU offload for llama.cpp models by default CI #434: Pull request #194 opened by james-333i
Action required james-333i:feat/llama-gpu-offload
james-333i:feat/llama-gpu-offload
Action required
Fix LlamaLanguageModel build against current llama.swift CI #433: Pull request #193 opened by james-333i
Action required james-333i:fix/llama-penalties-api
james-333i:fix/llama-penalties-api
Action required
Add an assistant prefill option to LlamaLanguageModel CI #432: Pull request #192 opened by james-333i
Action required james-333i:feat/llama-assistant-prefill
james-333i:feat/llama-assistant-prefill
Action required
Ingest decoder prompts in batch-sized chunks CI #430: Pull request #190 opened by james-333i
-1s james-333i:fix/llama-chunked-prompt
james-333i:fix/llama-chunked-prompt
-1s
Deliver streamed tokens live instead of after generation completes CI #429: Pull request #189 opened by james-333i
-1s james-333i:fix/llama-token-streaming
james-333i:fix/llama-token-streaming
-1s
Enable Metal GPU offload for llama.cpp models by default CI #428: Pull request #188 opened by james-333i
Action required james-333i:feat/llama-gpu-offload
james-333i:feat/llama-gpu-offload
Action required
Accept stringified primitives in Generable conversions CI #425: Pull request #185 opened by james-333i
Action required james-333i:fix/tool-argument-string-coercion
james-333i:fix/tool-argument-string-coercion
Action required
Route think and keep_alive to the top level of Ollama chat requests CI #424: Pull request #184 opened by james-333i
Action required james-333i:fix/152-ollama-think
james-333i:fix/152-ollama-think
Action required
Send images per message in Ollama chat requests CI #423: Pull request #183 opened by james-333i
Action required james-333i:fix/167-ollama-vision-images
james-333i:fix/167-ollama-vision-images
Action required
Support tool calling in MLXLanguageModel.streamResponse() CI #422: Pull request #181 opened by noorbhatia
Action required noorbhatia:mlx-stream-toolcall
noorbhatia:mlx-stream-toolcall
Action required
Fix three places where constrained JSON generation ignores the model CI #421: Pull request #180 opened by asaptf
Action required asaptf:fix/constrained-generation-arbitrary-choices
asaptf:fix/constrained-generation-arbitrary-choices
Action required
Bump actions/checkout from 7.0.0 to 7.0.1 in the actions group CI #420: Pull request #179 opened by dependabot Bot
47s dependabot/github_actions/actions-7a5a078ad4
dependabot/github_actions/actions-7a5a078ad4
47s
github_actions in /. - Update #1499330513 Dependabot Updates #2: by dependabot Bot
41s main
main
41s
Restore instructions from transcript (#156) CI #413: Commit f22b78e pushed by pcuenca
59s main
main
59s
Bump the actions group with 2 updates (#173) CI #412: Commit 0ad0b29 pushed by pcuenca
2m 41s main
main
2m 41s
Bump the actions group with 2 updates CI #411: Pull request #173 opened by dependabot Bot
2m 54s dependabot/github_actions/actions-ebbb40756a
dependabot/github_actions/actions-ebbb40756a
2m 54s
github_actions in /. - Update #1445620587 Dependabot Updates #1: by dependabot Bot
54s main
main
54s