sgl-project/sglang · error · ValueError

Invalid {self.patch_size=}. Must be > 0.

Error message

Invalid {self.patch_size=}. Must be > 0.

What it means

LTX-2 pipeline config requires patch_size > 0 before computing post-patch token counts for SP time-sharding of packed token latents. patch_size is used both as a divisor for latent height/width and later to compute tokens_per_frame, so a non-positive value breaks the arithmetic. This ValueError fires when the transformer patch size is 0 or negative.

Source

Thrown at python/sglang/multimodal_gen/configs/pipeline_configs/ltx_2.py:340

        self, batch, seq_len: int
    ) -> tuple[int, int]:
        """Infer latent-frame count and tokens-per-frame for packed token latents [B, S, D].

        Notes:
        - This assumes `patch_size_t == 1` (no temporal patching).
        - Tokens are ordered as (frame, height, width) after packing.
        """
        if int(self.patch_size_t) != 1:
            raise ValueError(
                "LTX-2 SP time-sharding for packed token latents currently requires "
                f"{self.patch_size_t=}. (Expected 1)"
            )
        if int(seq_len) <= 0:
            raise ValueError(f"Expected {seq_len=} > 0 for packed token latents.")
        if int(self.vae_scale_factor) <= 0:
            raise ValueError(f"Invalid {self.vae_scale_factor=}. Must be > 0.")
        if int(self.patch_size) <= 0:
            raise ValueError(f"Invalid {self.patch_size=}. Must be > 0.")

        latent_height = int(batch.height) // int(self.vae_scale_factor)
        latent_width = int(batch.width) // int(self.vae_scale_factor)
        if latent_height <= 0 or latent_width <= 0:
            raise ValueError(
                "Invalid latent H/W computed from batch.height/width: "
                f"{batch.height=} {batch.width=} {self.vae_scale_factor=}"
            )
        if (latent_height % int(self.patch_size)) != 0 or (
            latent_width % int(self.patch_size)
        ) != 0:
            raise ValueError(
                "Invalid spatial patching for packed token latents. Expected latent H/W "
                "to be divisible by patch_size, got "
                f"{latent_height=} {latent_width=} {self.patch_size=}."
            )

        post_patch_h = latent_height // int(self.patch_size)

View on GitHub (pinned to 0132848349)

Solutions

1. Set patch_size to the model's actual spatial patch size (commonly 2 for LTX-2 packed token latents)
2. Verify the config dict key name matches what the loader expects and prints the resolved value before use
3. Assert positivity of all patch fields when constructing the config

Example fix

// before
config.patch_size = 0
config.shard_latents_for_sp(batch)  # ValueError

// after
config.patch_size = 2
config.shard_latents_for_sp(batch)

assert config.patch_size and int(config.patch_size) > 0, f"bad patch_size={config.patch_size}"

When it happens

Trigger: Calling shard_latents_for_sp on a config where patch_size is 0 or negative, e.g. a config dict missing the patch_size key and defaulting to 0, or a bad override.

Common situations: Hand-edited or programmatically generated LTX-2 configs that omit or corrupt patch_size; version changes that renamed the config key (e.g. patch_size vs spatial_patch_size) leaving the old key unset.

Understand the failure class

Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.

Related errors

• Invalid {self.vae_scale_factor=}. Must be > 0.
• Invalid latent H/W computed from batch.height/width: {batch.
• Invalid tokens_per_frame={tokens_per_frame} from {latent_hei
• LTX-2 token latents seq_len={seq_len} is not divisible by to
• LTX-2 SP time-sharding for packed token latents currently re

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/5b0a53f4ba22d5b9. Report an issue: GitHub.