eeich
3c1258ef98
- Update to 0.30.6:
* Gemma 4 QAT weights: the Gemma 4 family is now optimized with
Quantization-Aware Training (QAT) to dramatically reduce memory
requirements and maximize on-device performance.
* ollama launch omp now integrates with Oh My Pi, an AI coding
agent with IDE integration
- update to 0.30.5:
* Fix gemma4:12b floating point exception crash
* llama.cpp version update
* models: add support for gemma4-12b
- update to 0.30.2:
* feat(launch): show and auto-install Cline CLI
* log template details to aid troubleshooting
* cmd/launch: add Qwen code integration
* launch: fix opencode local model limits
* llm: include cached prompt tokens in llama-server counts
* Harden app markdown URL handling
* discover: allow Radeon 8060S iGPU
* llm: detect llama-server load stalls from output
* More harden app markdown URL handling
* llama.cpp version update
* launch: isolate Codex launch configuration
* llama: add laguna (poolside) arch via a llama.cpp patch under llama/c…
* docs: configure hermes desktop app
* llm: ignore llama-server SSE ping comments
* fix laguna patch build breakage
* llama.cpp b9478 added a default 30s SSE ping that emits colon-only
comment frames (":\n\n") while streamed requests are idle; Ollama
OBS-URL: https://build.opensuse.org/request/show/1358005
OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/ollama?expand=0&rev=171
5 lines
91 B
Plaintext
5 lines
91 B
Plaintext
name: mlx
|
|
version: main
|
|
mtime: 1779577633
|
|
commit: 2165dc08d7b33258260aa849d39f087d50e62962
|