llama-burn + wgpu broken? #64
Description
Chip: Apple M3
OS: macOS 15.5 Beta (24F5042g)
Loading record...
Loaded in 7s
Processing prompt: How many helicopters can a human eat in one sitting?
thread 'main' panicked at /Users/visual/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/burn-jit-0.16.1/src/ops/float_ops.rs:366:89:
called `Result::unwrap()` on an `Err` value: CubeCountTooLarge
stack backtrace:
0: 0x104f69890 - <std::sys::backtrace::BacktraceLock::print::DisplayBacktrace as core::fmt::Display>::fmt::hfc1aec1722525aab
1: 0x104f852d4 - core::fmt::write::heccbd137bf61b5da
2: 0x104f66c90 - std::io::Write::write_fmt::haca8a96eb7cdccc9
3: 0x104f69744 - std::sys::backtrace::BacktraceLock::print::he7bfdc0a6bceeb9f
4: 0x104f6a8b8 - std::panicking::default_hook::{{closure}}::hcec2db2a6f3d4c4d
5: 0x104f6a708 - std::panicking::default_hook::hf79c7d86116dc29f
6: 0x104f6b398 - std::panicking::rust_panic_with_hook::h0e60ca225d10023a
7: 0x104f6afc4 - std::panicking::begin_panic_handler::{{closure}}::h40e919c7e63ca7fd
8: 0x104f69d48 - std::sys::backtrace::__rust_end_short_backtrace::ha5f082a0dfde6853
9: 0x104f6ac6c - __rustc[8a6480b3f5e8ef7f]::rust_begin_unwind
10: 0x104fc6c50 - core::panicking::panic_fmt::h6a23240c892a221a
11: 0x104fc6f88 - core::result::unwrap_failed::h800e5ed148294dcd
12: 0x1045549a4 - burn_jit::ops::float_ops::<impl burn_tensor::tensor::ops::tensor::FloatTensorOps<burn_jit::backend::JitBackend<R,F,I,BT>> for burn_jit::backend::JitBackend<R,F,I,BT>>::float_sum_dim::h6ff01a8fc1056efd
13: 0x10475c9d4 - <burn_fusion::ops::float::<impl burn_tensor::tensor::ops::tensor::FloatTensorOps<burn_fusion::backend::Fusion<B>> for burn_fusion::backend::Fusion<B>>::float_sum_dim::SumDimOps<B> as burn_fusion::stream::execution::base::Operation<<B as burn_fusion::backend::FusionBackend>::FusionRuntime>>::execute::h9f9dd9e2b4175fcd
14: 0x1045454b8 - <burn_fusion::stream::multi::Segment<R> as burn_fusion::stream::execution::processor::StreamSegment<<R as burn_fusion::backend::FusionRuntime>::Optimization>>::execute::h464d38ab66f48306
15: 0x104744820 - burn_fusion::stream::execution::processor::Processor<O>::process::hda54a04651839289
16: 0x104534bc0 - burn_fusion::stream::multi::MultiStream<R>::register::hd1dc0c5ae88111af
17: 0x10453a8d4 - <burn_fusion::client::mutex::MutexFusionClient<R> as burn_fusion::client::base::FusionClient<R>>::register::h79dba9616058be5a
18: 0x10473bf98 - burn_fusion::ops::float::<impl burn_tensor::tensor::ops::tensor::FloatTensorOps<burn_fusion::backend::Fusion<B>> for burn_fusion::backend::Fusion<B>>::float_sum_dim::hdba5107b19985a07
19: 0x10474ddc8 - burn_tensor::tensor::api::numeric::<impl burn_tensor::tensor::api::base::Tensor<B,_,K>>::sum_dim::hd59b4a39b225258c
20: 0x10466d4a4 - burn_core::nn::rope_encoding::RotaryEncoding<B>::apply::h9fee501d36b2d090
21: 0x104647a04 - llama_burn::transformer::Transformer<B>::forward::h53069aa98c209cb2
22: 0x1045fd56c - llama_burn::llama::Llama<B,T>::generate::h222f047d67bd5a9e
23: 0x10466e348 - chat::chat::h912c70a8ba9cfe6a
24: 0x10466eaf0 - chat::main::h642e6a68cbc5f844
25: 0x1046955ac - std::sys::backtrace::__rust_begin_short_backtrace::h765eb1ef42b9dd7d
26: 0x1047b3918 - std::rt::lang_start::{{closure}}::h82e09bbef9382677
27: 0x104f60ec8 - std::rt::lang_start_internal::hef6fb50dbdfc3bf8
28: 0x1046717b0 - _main