Batch-invariant inference nodes for guaranteed reproducibility in ComfyUI. ThinkingMachines + ECHO 2.0 + Nemotron patterns.
-
Updated
Jan 14, 2026 - Python
#
batch-invariance
Here are 6 public repositories matching this topic...
In bfloat16 a trainer gives the same token a different log probability depending on its batch shape; measured on 8 models, with the controls that survived
reinforcement-learning reproducibility numerics importance-sampling ppo bfloat16 trl llm rlhf vllm llm-training grpo verl batch-invariance
-
Updated
Sep 25, 2026 - Python
Batch-invariance verifier for llama.cpp continuous batching. Per-cell diffing, a five-verdict output contract, and signed GREEN or RED certificates. Mock-sourced passes are non-promotable by construction. 138 tests, CI green.
-
Updated
Aug 2, 2026 - Python
Bitwise batch-invariant matmul and attention kernels for MLX on Apple Silicon: identical logits at any batch size, with the harness that proves it.
python metal attention reproducibility quantization mlx gpu-kernels apple-silicon llm-inference batch-invariance deterministic-inference
-
Updated
Aug 31, 2026 - Python
量測 LLM 推論的決定性：同一 prompt 重複執行時，輸出從第幾個 token 開始分歧。
-
Updated
Aug 7, 2026 - Python
Measures whether an LLM inference engine returns the same tokens when requests share engine steps. Real results for OpenVINO GenAI on an Intel CPU and Arc iGPU.
benchmarking reproducibility determinism openvino llm-inference continuous-batching batch-invariance
-
Updated
Sep 15, 2026 - Python
Add this topic to your repo
To associate your repository with the batch-invariance topic, visit your repo's landing page and select "manage topics."