ViperEkura
b399d94de3
fix: add tokenizer thread-safety patch and disable frontend multiprocessing for image support
2026-06-15 14:05:31 +08:00
ViperEkura
3a3d0e2723
add modalities config for Qwen3-VL-8B-Instruct to enable image input
2026-06-15 14:02:04 +08:00
ViperEkura
9cbc7b0878
switch to Qwen3-VL-8B-Instruct, fix start.sh arg, enable tool calling with hermes parser
2026-06-15 14:01:04 +08:00
ViperEkura
917ff1c357
refactor server.py to use vLLM Python API and add permission config
...
server.py: switch from os.execvp(vllm) to make_arg_parser + asyncio.run(run_server(args)) for better error handling; add GPU selection via CLI argument
opencode.json: add default model field and permission.question=ask to prevent auto-triggering question tool
2026-06-14 20:51:00 +08:00
ViperEkura
b4490f26e2
update README with Qwen2.5 and manual start
2026-06-14 19:21:48 +08:00
ViperEkura
fe997f6522
log to project dir, add web.log to gitignore
2026-06-14 19:21:29 +08:00
ViperEkura
45adc385a0
fix: use model defaults for Qwen2.5, hermes parser
2026-06-14 19:15:35 +08:00
ViperEkura
62db1a70aa
switch to Qwen2.5-7B-Instruct
2026-06-14 19:08:43 +08:00
ViperEkura
b3caa7dd7b
add server, config, and scripts
2026-06-14 19:05:18 +08:00
110226d612
first commit
2026-06-14 18:54:46 +08:00
ViperEkura
jiachun