Wenbo Ji　嵇文博 4ebf11f7d9 [bugfix] Fix test env defaults and server dependencies (#1901) ...

The distributed_setup test fixture now sets MASTER_ADDR and MASTER_PORT when
they are not set, with a new port for each test, and restores them after the
test. pyproject.toml now declares orjson and python-multipart, which the
OpenAI-compatible server needs. Two documents about the SSIM reference
bootstrap are corrected.

2026-10-07 15:32:22 -07:00

..

api

[bugfix] Return individual images for batched image API requests (#1917)

2026-10-07 15:06:02 -07:00

attention

[perf] Fuse VSA64 tile layout for SM100 inference (#1900)

2026-10-07 15:31:58 -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

[feat] Add external-launcher executor for multi-node inference (#1746)

2026-10-07 04:46:26 -07:00

dataset

[bugfix] Prevent ParquetDatasetWriter from overwriting shards across flushes (#1922)

2026-10-07 14:56:53 -07:00

distributed

[perf] Harden Ulysses agreement and tune bounded H3 transfers (#1807)

2026-10-07 04:01:53 -07:00

encoders

[new-model] Add Cosmos Predict2.5 distilled T2W and DFD V2W inference (#1767)

2026-10-07 04:42:44 -07:00

entrypoints

[bugfix] Return individual images for batched image API requests (#1917)

2026-10-07 15:06:02 -07:00

eval

[feat] Add end-to-end MMAudio V2A training, inference, and evaluation (#1648)

2026-10-07 04:25:00 -07:00

golden_gate

[misc] Move test-suite environment access into the registry and allowlists (#1898)

2026-09-30 00:15:39 -07:00

hooks

[feat]: FastH3 on single RTX GPUs (#1919)

2026-10-06 11:37:01 -07:00

inference

[perf]: QAT/QAD add safe regional compile for modular training (#1718)

2026-10-07 05:24:24 -07:00

layers

[perf] Wan kernel fusion: Triton-fused residual+LayerNorm+modulate inference path (#1708)

2026-10-07 04:08:07 -07:00

loader

[bugfix] Fix the CUDA device of Ray workers on multi-GPU nodes (#1932)

2026-10-07 15:00:23 -07:00

lora_extraction

[feat] Add streaming and GPU-accelerated LoRA extraction (#1784)

2026-10-07 04:48:35 -07:00

mlx

[feat]: FastH3 on DGX Spark and Apple Silicon (#1920)

2026-10-06 12:17:11 -07:00

modal

[ci] Separate performance behavior tests (#1620)

2026-10-07 03:43:12 -07:00

nightly

[misc]: Refactor separate training pipeline runner (#1696)

2026-10-07 03:19:21 -07:00

ops

[bugfix]: retain NVFP4 weights for LTX2 refinement LoRA (#1705)

2026-10-07 03:29:46 -07:00

performance

[ci] Separate performance behavior tests (#1620)

2026-10-07 03:43:12 -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

[bugfix]: fix the MLX server and a GPU-only test leak after the 2026-10-07 merges (#1931)

2026-10-07 14:35:05 -07:00

schedulers

[new-model] Add Cosmos Predict2.5 distilled T2W and DFD V2W inference (#1767)

2026-10-07 04:42:44 -07:00

ssim

[bugfix] Fix test env defaults and server dependencies (#1901)

2026-10-07 15:32:22 -07:00

stages

[feat] Add external-launcher executor for multi-node inference (#1746)

2026-10-07 04:46:26 -07:00

train

[perf]: QAT/QAD add safe regional compile for modular training (#1718)

2026-10-07 05:24:24 -07:00

training

[bugfix] LTX-2: train temporal RoPE at the clip's fps (#1892)

2026-10-07 14:54:34 -07:00

transformers

[bugfix] Fix HunyuanVideo forward pass with batch size greater than one (#1921)

2026-10-07 15:15:12 -07:00

vaes

[feat]: FastH3 on single RTX GPUs (#1919)

2026-10-06 11:37:01 -07:00

worker

[bugfix] Return individual images for batched image API requests (#1917)

2026-10-07 15:06:02 -07:00

workflow

[feat]: add MiniMax H3 Ref2VA and LoRA training support (#1757)

2026-10-07 03:21:45 -07:00

__init__.py

[Feature] Remove V1 folder (#642)

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

AGENTS.md

[ci] Separate performance behavior tests (#1620)

2026-10-07 03:43:12 -07:00

conftest.py

[bugfix] Fix test env defaults and server dependencies (#1901)

2026-10-07 15:32:22 -07:00

test_logger.py

[misc]: add env var to control process-aware logging (#1680)

2026-10-07 04:31:52 -07:00

test_partial_hf_download.py

[feat] FastH3 Ref2VA PDD inference with reference-video VSA sparsity (#1907)

2026-10-02 11:28:07 -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