7th

ml • mechE • plus ultra and things of that nature

[7th @fw7th]

I'll allot intentional time to attack these in the days following this post.

I'll need some sort of yardstick to measure myself against. I'll work problem sets involving system design.
I'll also focus on seeing more design decisions, systems and implementation details.

[7th @fw7th]

Day 4/? Inference engine.
Since my main goal of doing this was to improve my overall skills, I've identified two bottlenecks.

1. I design inefficient systems/modules under uncertainty.
2. My programming knowledge is very basic/rudimental albeit I complete projects with it.

[7th @fw7th]

@laurathesimp The answer is simply; balls of steel. Something you don't seem to possess

[7th @fw7th]

@snwy_me probably ragebait

[7th @fw7th]

@snwy_me of tokens?

[7th @fw7th]

@k7agar When it's paid compute too

[7th @fw7th]

@shiri_shh His voice sounds like Sam Altman's

[7th @fw7th]

@pa1nark @pepeller @shiri_shh Best comment lmao

[7th @fw7th]

@realcryobyte @schteppe Forgot to add "make no mistaes, I give you the power of 4 senior develops",

rookie mistake

[7th @fw7th]

@schteppe I love how some comments can't tell his is a joke 😭

[7th @fw7th]

@wildmindai what kind of algorithm is used for gazing, it seems about like temporal averaging or optical flow

[7th @fw7th]

@probnstat What kind of data?
And what are the inductive biases of deep net?
What's our measure of performance?

I think further questions would need to be asked no?

[7th @fw7th]

@jino_rohit I don't maintain any repos, is it really that bad?

[7th @fw7th]

Training Frameworks: Ops are API functions called by tensors. Tensors track what tensors created them and the ops used.

This took me some time to figure out.
Got frustrated;

- re-read attention is all you need
- Revised Inner product spaces
- studied for fluid mechanics test

[7th @fw7th]

Day 3: ML inference engine
Op kernels for inference engines e.g ggml, are different from ML frameworks e.g tinygrad & pytorch.

Here's the difference:
inf. Engines: build a static graph of predefined ops, some libs abstract away tensors and ops to a "layer", no grad tracking.

[7th @fw7th]

@dogecahedron say i had 3 rows and 2 cols, I would store stride=2 (row major), then "append" subsequent rows, but how do you scale it to n-D?

[7th @fw7th]

day2: CPU inference engine
1d and 2d tensors working, but it's kind hacky;

1. Custom allocator but just a wrapper around malloc and free with some attachments.

2. implementation now allocates contiguous memory based on sizeof(dtype) * w for a 1d tensor. Tensors are row-major

[7th @fw7th]

@dogecahedron lemme my understanding; stride will allow me to traverse along one dim, and then subsequent rows/cols along that same dim so I store it as a contiguous array in memory?

[7th @fw7th]

3. For 2d tensors I figured out how to map to a contiguous array with;
(i * n_cols) + j. Tensors can be randomly filled or with a specific number

This won't scale to n-D tensors so I'll probably redesign this in the future.

My aim for now is to write all ops.

[7th @fw7th]

@jino_rohit To what extent do you wanna add features?