[faresobeid]

SamplingMask.from_sampling_mask now also accepts prime-rl's packed CSR form.

prime-rl's /inference/v1/generate server now returns sampling masks as {"ids": {data, shape, dtype}, "counts": {data, shape, dtype}} (base64 int32 arrays) instead of list[list[int]]. The one-list-per-token form was a large part of the vLLM API server's GC load and JSON size under RL traffic (see the prime-rl PR). Here it also skips building one Python list per token when the client parses the response.

• dict input: decode ids and counts straight into the existing int32 arrays (_decode_packed, which feat(v1): optional sampler logprobs on SamplingMask #2756 reuses for its packed logprobs).
• list input (stock vLLM): unchanged.

Companions: renderers PrimeIntellect-ai/renderers#174 / prime-rl PrimeIntellect-ai/prime-rl#3900. Land renderers -> verifiers -> prime-rl; the prime-rl submodule pins must move to the merged commits.

Validation

• tests/v1/test_trace.py tests/v1/test_graph.py: pass (one new test: packed and list inputs give the same arrays).
• ruff check / ruff format (0.16.0) on the changed files: clean.

---

Note

Low Risk
Additive parsing path with existing list behavior preserved; main caveat is packed shape is not validated during decode.

Overview
Extends SamplingMask.from_sampling_mask so verifiers can ingest prime-rl’s packed CSR sampling masks from /generate, not only vLLM’s per-token list[list[int]] form. When the input is a dict with ids and counts, each value is decoded via a new _decode_packed helper (base64 data + dtype → numpy int32 arrays) instead of concatenating Python lists per token.

List-based input is unchanged. A unit test asserts packed and list representations yield the same ids and counts arrays.

^{Reviewed by Cursor Bugbot for commit 8f1a6ce. Bugbot is set up for automated code reviews on this repo. Configure here.}

Note

Accept packed CSR sampling masks in SamplingMask.from_sampling_mask

• SamplingMask.from_sampling_mask in types.py now accepts either the existing list-of-lists input or a dict with packed ids and counts arrays, matching prime-rl's /generate format
• Adds a _decode_packed helper that base64-decodes the packed data, interprets it with the packed dtype, and casts to the requested dtype
• Adds a test in test_trace.py verifying that list and packed inputs produce identical ids and counts arrays
• Risk: the packed shape metadata in _decode_packed is ignored; the arrays are reconstructed only from counts and ids

^{Macroscope summarized 8f1a6ce.}

[macroscopeapp]

Approvability

Verdict: Approved at ec0bbed

Macroscope's review found this PR approvable — This is a narrowly scoped compatibility enhancement that decodes prime-rl’s packed sampling-mask payload into the existing representation while preserving the list-based path. The behavior is covered by a focused equivalence test and does not affect schemas, deployment, security, or other production workflows.

No code changes detected at 8f1a6ce. Prior analysis still applies.

^{You can add or adjust custom eligibility rules. Learn more.}