crucible-runtime

2 Commits 1 Branch 1 Tag

2 Commits

Author	SHA1	Message	Date
pierreandLetta Code	a2ff07234c	fix(linear): add bias once, not once per SIMD lane acc was seeded with @splat(bias) and reduced with .Add, so every linear output carried 7 extra copies of its bias. conv2d was unaffected (bias via memset), which is why the trunk matched zig-solver to 5e-6 while fc/head activations diverged — the 81% labels regression. Also adds a scalar tail for in_n < 8 (pose_fc has in_n=4) and a known-answer selftest (test_linear). 👾 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta Code <noreply@letta.com> v0.1.1	2026-09-29 22:08:45 +03:00
pierreandLetta Code	d401f6b07e	crucible v0.1: CPU inference library for PyTorch .pt state dicts, in pure Zig - restricted pickle VM (whitelisted globals — cannot execute arbitrary Python, unlike torch.load) - zip container reader (store + raw-deflate) - Tensor views: dtype/offset/sizes/strides, f32 materialization - layers: conv2d f32x8 FMA, linear, relu, maxpool2, adaptiveAvgPool2d, softmax, padInput - examples/stripsolver: real .pt forward, 3777 @ 1.0 👾 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta Code <noreply@letta.com>	2026-09-29 18:41:46 +03:00

Author

SHA1

Message

Date

pierreandLetta Code

a2ff07234c

fix(linear): add bias once, not once per SIMD lane

acc was seeded with @splat(bias) and reduced with .Add, so every
linear output carried 7 extra copies of its bias. conv2d was unaffected
(bias via memset), which is why the trunk matched zig-solver to 5e-6
while fc/head activations diverged — the 81% labels regression.

Also adds a scalar tail for in_n < 8 (pose_fc has in_n=4) and a
known-answer selftest (test_linear).

👾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta Code <noreply@letta.com>

v0.1.1

2026-09-29 22:08:45 +03:00

pierreandLetta Code

d401f6b07e

crucible v0.1: CPU inference library for PyTorch .pt state dicts, in pure Zig

- restricted pickle VM (whitelisted globals — cannot execute arbitrary
  Python, unlike torch.load)
- zip container reader (store + raw-deflate)
- Tensor views: dtype/offset/sizes/strides, f32 materialization
- layers: conv2d f32x8 FMA, linear, relu, maxpool2, adaptiveAvgPool2d,
  softmax, padInput
- examples/stripsolver: real .pt forward, 3777 @ 1.0

👾 Generated with [Letta Code](https://letta.com)

Co-Authored-By: Letta Code <noreply@letta.com>

2026-09-29 18:41:46 +03:00