candle
candle copied to clipboard
huggingface
Minimalist ML framework for Rust
# What does this PR do? Add support for Qwen-2.5-VL ## Part of Issue #2814
Is the new gpt-oss-20b a totally different architecture or can I use an existing candle setup, swap out the files and start playing around with gpt-oss-20b?
I'm trying to call some image-to-text visual models using candle, if anyone knows how to use Qwen2.5-vl or Fast-VLM, can you share it? Appreciate
Cuda 12.9 4090 linux system compiles everything fine but the rwkv models loop insane responses: ```rust $ ./target/release/examples/rwkv --which eagle7b --quantized --prompt "one word answer then terminate" avx: true, neon:...
Candle currently has limited documentation, and there doesn’t seem to be a Korean translation available yet. I would be happy to contribute by improving the documentation and providing a Korean...
# What does this PR do? Implemented voxtral and examples in candle. ## Issue Part of #3028 ## Requirements - [ ] Need fixes to fully run the code
if there any plan to support some VL models such as Qwen2.5 VL and some TTS model like SparkTTS etc?
I’m trying to build a Rust project locally that depends on candle-kernels on my laptop with an NVIDIA GeForce 940MX (Maxwell, compute capability 5.0). The build fails with errors like:...
When I try to build and run a llama 3.2 1b model on iOS (iPhone 14) with flash attention on Metal, I get ``/Users/jpchen/.cargo/git/checkouts/candle-6740f55d69a3bf41/b4ec636/candle-transformers/src/models/llama.rs:254:5: not implemented: compile with '--features flash-attn'`...
