paddle-mobile将开发一个新的版本，为了：

• 支持Paddle Fluid
• 更小的体积
• 更快的速度
• 更广泛地支持各种arm设备和终端平台

因此，paddle-mobile将会进行一次完全的重构，从框架设计到代码开发。在新版本开发完成后，将会删除原有mobile-deep-learning的代码。新版本开发期间，代码将放置在paddle-mobile repo的一个子目录下。对于子目录的命名，目前有3个候选，希望大家投票：

• 👍 zygote
• 👎 paddle
• ❤️ fluid

有更好的建议，请回复issue。相关issue：#121
另外，待新版本代码开发完成，移除老版本mobile-deep-learning代码后，新版本代码将移出子目录，直接放置在paddle-mobile repo下面。

Is your enhancement proposal related to a problem? Please describe.
Syscalls run on fixed-sized privilege elevation stacks. There is a hard limit on how much stack space a system call can use because of this. We don't have good data on how much stack syscalls actually use.

Describe the solution you'd like
I'd like to be able to use CONFIG_STACK_USAGE to be able to generate a report,

Implement Python 3 bindings, so wasm3 can be easily used from Python.

Resurrecting the second bullet from #1334

• Figure out how to fix favicon / logo more generally (here's a start https://github.com/tock/tock/tree/doc-updates)

MICROPY_PY_COLLECTIONS_ORDEREDDICT is set individually for every port. We should centralize it's use to py/circuitpy* settings. MICROPY_CPYTHON_COMPAT is an example of a setting that has already been centralized.

../../ports/unix/mpconfigport.h
102:#define MICROPY_PY_COLLECTIONS_ORDEREDDICT (1)

../../ports/nrf/mpconfigport.h
63:#define MICROPY_PY_COLLECTIONS_ORDEREDDICT       (1

Dhcpv4Client ignores the device checksum capabiltities, and always uses the default value for ChecksumCapabilities. The code responsible can be seen here:
https://github.com/smoltcp-rs/smoltcp/blob/bdfa44270e9c59b3095b555cdf14601f7dc27794/src/dhcp/clientv4.rs#L133

As far as I can tell, this would basically be a one-line fix:

let checksum_caps = iface.device().capabilities().check