Spaces:
Runtime error
Runtime error
Commit History
-
docs: add technical report for codex handoff (2026-06-13)
J.B-Lin348adcc
-
refactor: deprecate llama-omni-server, use llama-server built-in omni endpoints
J.B-LinKey findings: - llama-server (server.cpp) natively provides /v1/stream/* omni endpoints - It reuses already-loaded LLM model+ctx, no need for separate omni server - llama-omni-server was an experimental standalone binary Changes: - Image recipe: build llama-server only (remove llama-omni-server target) - serve() lifespan: single llama-server process only (remove omni subprocess) - Omni endpoint proxy: point to llama-server port 8081 (remove OMNI_SERVER_PORT) - Clean up tmp_*.py test files Status: Image im-kINUqibAmbYIS6brxSIOIY deployed (4737s build)6451051
-
modal/omni: PRODUCTION DEPLOY - text inference fully verified, llama-server running on T4
J.B-Lin- Chinese: 1.0s, '你好，我是MiniCPM系列模型...' (finish_reason=stop) - English: 1.8s, 'The capital of France is Paris.' (finish_reason=stop) - Cold start: 11s model load on T4 - --jinja flag confirmed working for correct chat template - Production URL: https://andrew-jiabin--prego-pal-minicpm-omni-serve.modal.run Next: add omni voice endpoints (prefill/generate/break) for full-duplex audiod7f81b5 -
modal/omni: text inference verified (Chinese OK, English needs fix)
J.B-Lin- Chinese reply correct: '你好，我是MiniCPM系列模型...' - English empty due to finish_reason=length (50 special tokens before valid text) - Added --jinja flag to fix chat template formatting - Improved test logging: show content, finish_reason, usage per test - Serve function already had --jinja (confirmed correct) - Updated docs with real test results2400b46 -
modal/omni: llama-server inference verified on T4
J.B-Lin- test_inference: non-blocking stderr reader (thread+queue) - test_inference: --mmproj only vision (no comma-sep, no audio) - test_inference: timeout 600s->900s - serve: --mmproj only vision (was comma-sep vision+audio) - docs: add test results (11s cold start, 1s inference on T4) - docs: fix mmproj documentation (only ONE file, audio via API)0e9e62e -
docs: add production script protect warnings to deploy guide
J.B-Lin10796de -
docs: comprehensive Modal deploy guide (both solutions + pitfalls)
J.B-Lin03e9a7c -
deploy_omni: llFile llama.cpp-omni compile succeeds on Modal T4
J.B-Lin- CUDA Toolkit 12.4 + cuda-compiler + cuda-driver-dev from NVIDIA apt repo - GGML_CUDA_NO_VMM=ON to avoid libcuda.so.1 linking in build phase - CUDA arch 75 (T4) + 89 (L4) - LLAMA_CUDA_FORCE_MMQ=ON for faster compilation - Source from tc-mb/llama.cpp-omni fork, stored in modal_deploy/llamacpp_omni/ - Build time ~77 min on Modal infra Resolves: modal deploy build failures due to GitHub access and CUDA linking1a07461 -
[PregoPal] 2026-06-11 全双工语音对话开发阶段完成
J.B-Lin## 核心改动 - API_BASE 修复: voice_helper 指向 PregoAPI(8090) 而非 llama-server(8081) - server_name 改为 0.0.0.0:7889 (Tailscale 远程访问支持) - 前端全双工 UI: CSS隐藏上传框 / JS自动触发录音 / 按钮状态切换 - docs/技术报告_2026-06-11.md: 完整技术文档 (含架构图/API/已知问题/下一步) ## 验证状态 - 后端链路验证通过: chat_voice(测试WAV) → AI中文回复 + TTS音频输出 - CDP前端交互验证: 按钮切换 / 自动录音 / 状态显示 均正常 - 三服务运行正常: PregoPal(7889) + PregoAPI(8090) + llama-server(8081)50a87dc
-
docs: 更新开发日志和本地部署经验，记录全双工实现细节
J.B-Lina911bdf -
用户手动备份
J.B-Lin2ce3e61 -
技术路径
J.B-Lin8eb4628 -
用户手动整理文件，并备份deploy_backup.py文件
J.B-Lin68d23d2 -
docs: 部署成功报告 + 清理神秘文件 c
J.B-Lin56b0dc2 -
docs: 补充两种方案对比(wheel vs 源码编译)，明确预编译wheel仍属llama.cpp
J.B-Lin2e5f272 -
docs: 技术日志-解释为什么预编译wheel部署这么快
J.B-Linb7e6626
-
docs: pre-refactor backup - before tech log integration
J.B-Lind14aeea -
refactor: 合并三天总结到营养报告，移除独立Tab
J.B-Lin153f3f8 -
docs: 新增项目架构说明书，包含完整模块分析、数据文件状态、协作规范与待办事项
J.B-Line179fe6 -
docs: 更新部署日志 - Modal修复记录+API设计
J.B-Linec87820 -
docs: 更新开发日志 - 添加 deploy.py 已知问题4项 + 编译状态
J.B-Lin30f103b -
docs: 更新部署经验文档和gitignore - 添加部署状态/API URL/清理规则
J.B-Lindc0f265 -
feat(modal): 部署 MiniCPM-o 4.5 到 Modal (llama.cpp + FastAPI)
J.B-Lin09159ca -
docs: update 开发日志 with UI redesign iterations
J.B-Lin75c2435 -
feat: llama.cpp deploys MiniCPM-o 4.5 on Modal - technical report and client API
J.B-Linff5d4ed
-
chore: save current version before UI improvements (i18n + font fix)
J.B-Linec90eae -
CLine 界面初版
J.B-Lin0f2d3d7