Skip to content

(2) FA4 support (sglang-fa4 -> sglang)#3

Open
avnermay wants to merge 13 commits intoavner/sglangfrom
avner/sglang-fa4
Open

(2) FA4 support (sglang-fa4 -> sglang)#3
avnermay wants to merge 13 commits intoavner/sglangfrom
avner/sglang-fa4

Conversation

@avnermay
Copy link
Copy Markdown
Collaborator

No description provided.

@avnermay avnermay changed the title FA4 support FA4 support (sglang-fa4 -> sglang) Mar 28, 2026
@avnermay avnermay changed the title FA4 support (sglang-fa4 -> sglang) (2) FA4 support (sglang-fa4 -> sglang) Mar 28, 2026
self.block_size = config.kvcache_block_size
self.enforce_eager = config.enforce_eager
self.tokenizer = AutoTokenizer.from_pretrained(config.tokenizer_path if config.tokenizer_path else config.model, use_fast=True)
self.tokenizer = AutoTokenizer.from_pretrained(config.tokenizer_path if config.tokenizer_path else config.model, use_fast=True, trust_remote_code=True)
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Static Code Analysis Risk: Together python huggingface trust remote code

trust_remote_code=True downloads and executes arbitrary Python code from the model repository without sandboxing (OWASP LLM03:2025 Supply Chain). A malicious or compromised model repo can achieve RCE on every host that loads the model (CWE-94). Pin to a verified commit hash and audit remote code before use, or use models that don't require trust_remote_code.

Severity: High 🚨
Status: Open 🔴

References:

  1. https://cwe.mitre.org/data/definitions/94
  2. https://huggingface.co/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained
  3. https://genai.owasp.org/llmrisk/llm032025-supply-chain/
  4. https://hiddenlayer.com/research/weaponizing-machine-learning-models-with-ransomware/

Suggested reviewers 🧐: @avnermay

More details:

🌻 View in Arnica

If you see an issue, please contact Shasheen in the #security-engineering Slack channel.


Take action by replying with an [arnica] command 💬

Actions

Use [arnica] or [a] to interact with the Arnica bot to acknowledge or dismiss code risks.

To acknowledge the finding as a valid code risk: [arnica] ack <acknowledge additional details>

To dismiss the risk with a reason: [arnica] dismiss <fp|accept|capacity> <dismissal reason>

Examples

  • [arnica] ack This is a valid risk and I'm looking into it

  • [arnica] dismiss fp Dismissed - Risk Not Accurate: (i.e. False Positive)

  • [arnica] dismiss accept Dismiss - Risk Accepted: Allow the risk to exist in the system

  • [arnica] dismiss capacity Dismiss - No Capacity: This will need to wait for a future sprint

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant