Comments (3)
By the way, version nitro-0.3.22-win-amd64-avx-cuda-12-0.tar.gz doesn't launch at all. Even as a command line.
from nitro.
I tried running nitro-0.3.21-win-amd64-avx-cuda-12-0.tar.gz via command line and this is what came out! I don't understand why I'm being asked for AVX2!
λ curl http://localhost:5000/inferences/llamacpp/loadmodel -H 'Content-Type: application/json' -d '{"cpu_threads":5,"ctx_len":2048,"prompt_template":"<|system|>\n{system_message}<|user|>\n{prompt}<|assistant|>","llama_model_path":"S:\\JAN\\models\\tinyllama-1.1b\\tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf","system_prompt":"<|system|>\n","user_prompt":"<|user|>\n","ai_prompt":"<|assistant|>","ngl":100}'
{"message":"AVX2 is not supported by your processor, please download and replace the correct Nitro asset version"
from nitro.
Last version nitro-0.3.18-win-amd64-avx-cuda-12-0.tar.gz without avx2 error
but exit
20240509 10:09:47.865000 UTC 9568 INFO Nitro version: - main.cc:50
20240509 10:09:47.867000 UTC 9568 INFO Server started, listening at: 127.0.0.1:5000 - main.cc:54
20240509 10:09:47.867000 UTC 9568 INFO Please load your model - main.cc:55
20240509 10:09:47.867000 UTC 9568 INFO Number of thread is:8 - main.cc:62
{"timestamp":1715249390,"level":"INFO","function":"LoadModelImpl","line":646,"message":"system info","n_threads":5,"total_threads":8,"system_info":"AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 | "}
curl: (56) Recv failure: Connection was reset
from nitro.
Related Issues (20)
- epic: Model Endpoint: Download, Load, Unload HOT 1
- epic: Research embedding lua c++ HOT 1
- epic: Orchestrator HOT 1
- epic: Kernel HOT 2
- epic: Queue
- epic: Threads & Messages
- epic: Pluggable Inference Engines HOT 1
- bug: weird responses from nitro when cache enabled HOT 2
- feat: ARM support on Linux
- feat: Migration from coupled server to engine - Python Sub System HOT 2
- feat: Migration from coupled server to engine - llamacpp HOT 1
- feat: Migration from coupled server to engine - trt-llm HOT 1
- feat: /engines - model engines listing endpoint HOT 1
- feat: Refactor Cortex Monorepo HOT 2
- feat: Cortex Backend Auth
- feat: integrate python-runtime as an engine HOT 1
- bug: Importing Nitro/Cortex OpenAPI Specification (YAML) Files Fails in Postman, While OpenAPI Specification Files Import Successfully HOT 1
- feat: Support for multilingual embedding models and simultaneous hosting of LLM & embedding models HOT 1
- feat: Multible Documents(PDF) for Embedding HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nitro.