Aryan KumarandAryan Kumar f82d8be4bf [perf] Sequential MiniMax H3 start with GPU-direct DiT load (#1793) ...

Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>

2026-08-31 04:20:21 -07:00

..

api

[bugfix] Harden OpenAI serving after post-merge review (#1782)

2026-08-28 22:29:24 -07:00

attention

[perf] Align FastH3 optimized inference profile (#1748)

2026-08-23 02:01:03 -07:00

audio

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

contract

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

dataset

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

distributed

[perf] Add fused NVLink all-to-all for Ulysses (#1740)

2026-08-22 23:06:24 -07:00

encoders

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

entrypoints

[bugfix] Harden OpenAI serving after post-merge review (#1782)

2026-08-28 22:29:24 -07:00

eval

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

golden_gate

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

hooks

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

inference

[perf] Sequential MiniMax H3 start with GPU-direct DiT load (#1793)

2026-08-31 04:20:21 -07:00

layers

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

loader

[feat] Add MiniMax H3 LoRA inference and preview launchers (#1771)

2026-08-27 14:43:39 -07:00

lora_extraction

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

mlx

[perf] Speed up exact MiniMax H3 MLX inference (#1792)

2026-08-31 04:14:55 -07:00

modal

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

nightly

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

ops

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

performance

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

pipelines

[perf] Disable every offload path on unified memory, unblocking MiniMax H3 generation on one GB10 (#1715)

2026-08-26 15:32:56 -07:00

platforms

[perf] Add MiniMax H3 MLX VSA and SIMD attention (#1776)

2026-08-30 13:44:54 -07:00

ssim

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

stages

[perf] Sequential MiniMax H3 start with GPU-direct DiT load (#1793)

2026-08-31 04:20:21 -07:00

train

[ci]: seed stable GB10 grad-norm references (#1756)

2026-08-30 03:09:18 -07:00

training

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

transformers

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

vaes

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

worker

[bugfix] Harden OpenAI serving after post-merge review (#1782)

2026-08-28 22:29:24 -07:00

workflow

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

__init__.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

AGENTS.md

[ci] make GPU validation change-aware (#1747)

2026-08-25 21:26:25 -07:00

conftest.py

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

test_partial_hf_download.py

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00

utils.py

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702)

2026-08-08 22:24:17 -07:00