dhiltgen
PulseAugur coverage of dhiltgen — every cluster mentioning dhiltgen across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Ollama v0.40.17-rc2 updates mlxrunner for memory pressure management
Ollama has released version v0.40.17-rc2, which includes an update to mlxrunner. This update adapts saved history to better manage memory pressure by retaining Metal prefix history based on observed memory headroom and …
-
Ollama releases v0.40.17-rc1 with mlxrunner speculative verification
Ollama has released version v0.40.17-rc1, introducing the mlxrunner feature for batch speculative verification. This update aims to improve concurrent generation by sharing target verification across requests while main…
-
Ollama v0.40.9-rc3 adds Gradium Phonon checkpoint support
Ollama has released version v0.40.9-rc3, which introduces support for Gradium Phonon checkpoints. This update replaces the prerelease checkpoint path with Gradium's GA format, includes default-voice import and speech co…
-
Ollama v0.40.9-rc2 fixes 'flint' replies with thinking disabled
Ollama has released version v0.40.9-rc2, which includes a fix for the 'flint' feature. This update ensures that replies are handled correctly when the 'thinking' functionality is disabled, allowing 'Flint' to provide di…
-
Ollama releases v0.40.6 with Windows runner fixes and cloud integration
Ollama has released version v0.40.6, introducing several updates and improvements. Key changes include preventing orphaned runners on Windows, adding new tensor and file types for GGUF, and launching Clef within Ollama'…
-
Ollama v0.40.11 adds macOS speech generation and vLLM integration
Ollama has released version v0.40.11, introducing several new features and improvements. The update enables speech generation on macOS, allowing users to play text or model replies aloud and stream audio via an OpenAI-c…
-
Ollama v0.40.0-rc1 updates mlx tokenizer semantics
Ollama has released version v0.40.0-rc1, which includes updates to its mlx integration. These changes focus on aligning tokenizer semantics with publisher standards, ensuring consistent handling of pretokenization, Unic…