---
license: apache-2.0
tags:
  - kv-cache
  - h2o
  - mla
  - long-context
  - inference-optimization
  - deepseek
  - kimi
library_name: transformers
---

# KV Cache Eviction for MLA-based Long-Context LLMs

A reference implementation of **H2O-style heavy-hitter + recency KV cache eviction** for transformer architectures that use **Multi-head Latent Attention (MLA)** as introduced in DeepSeek V3 and used in Kimi K2 / K2.6.

Maintained by **GENOMA LABS / research**.

---

## What this is

A drop-in monkey-patch for `DeepseekV3Attention` layers in HuggingFace `transformers` that adds importance-based KV cache eviction at inference time. **No retraining required.** The model loads normally; you call `install_kv_eviction(model, budget=4096)` and from that point eviction runs automatically during generation.

The technique is the canonical H2O recipe from Zhang et al., 2023 (NeurIPS 2023, [arXiv:2306.14048](https://arxiv.org/abs/2306.14048)) adapted to MLA's specific cache layout. Heavy hitters (tokens with the highest accumulated attention mass across all heads and layers) plus a small set of attention-sink tokens at the start and a recency window at the end are retained; the rest are evicted when the cache exceeds the budget.

## Why this matters

HuggingFace's reference MLA implementation caches the **expanded** K/V tensors, not the compressed latent. The cache footprint grows quickly:

| Context length | Full KV cache (canonical 61-layer DeepseekV3 layout) |
|---|---|
| 32K  |  ~82 GB |
| 128K | ~328 GB |
| 1M   | ~2.5 TB |

These numbers exceed available VRAM well before the model's nominal context window is reached. KV cache eviction is the lever that makes long-context inference economically viable on existing dense models without architectural changes or retraining.

| Eviction budget | Cache size (61 layers) |
|---|---|
| `budget=4096`   |  ~10.2 GB |
| `budget=8192`   |  ~20.4 GB |
| `budget=16384`  |  ~40.8 GB |

A 4096-token budget leaves ~70 GB free that would otherwise be cache. That headroom is where you fit longer prompts, larger batch sizes, or just keep more concurrent requests live on the same hardware.

## Compatible architectures

Verified against HuggingFace reference implementations of:

- **DeepSeek V3** and **V3.2** family
- **Kimi K2** and **K2.6** (uses the DeepseekV3Attention layer pattern)
- Any future MLA-based model that subclasses `DeepseekV3Attention`

For non-MLA architectures (standard MHA, GQA, MQA), the same H2O recipe applies, but the cache-management code paths differ and the patch in `src/kv_eviction_mla.py` would need adapting. Pull requests welcome.

## Quick start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from kv_eviction_mla import install_kv_eviction, reset_eviction_scores

model_id = "deepseek-ai/DeepSeek-V3"  # or moonshotai/Kimi-K2 etc.
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
tok = AutoTokenizer.from_pretrained(model_id)

# Patch the model in-place. Eviction runs automatically from this point.
install_kv_eviction(
    model,
    budget=4096,    # max KV tokens kept per layer (excluding sinks + recent)
    n_sink=4,       # tokens at start always kept
    n_recent=512,   # tokens at end always kept
    evict_every=1,  # evict every N generated tokens (1 = every step)
)

# Generate normally
inputs = tok("Your long prompt goes here...", return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(tok.decode(out[0]))

# Between independent generations, reset accumulated scores
reset_eviction_scores(model)
```

## How to choose a budget

The right budget depends on your workload's distribution of attention mass. Some recipes from the H2O paper and follow-on literature:

- **Streaming chat / code completion:** `budget=2048, n_sink=4, n_recent=256`. The recent window dominates; the budget acts as a memory of earlier-session context.
- **RAG / long-document QA:** `budget=4096, n_sink=4, n_recent=512`. Larger budget preserves the heavy-hitter facts in the middle of the document.
- **Code review / agent loops over large diffs:** `budget=8192, n_sink=4, n_recent=1024`. More budget for long technical context where the relevant facts can be anywhere.

Stress-test on RULER 128K NIAH or your own task-level evaluation before deploying. Eviction policies are workload-sensitive and the elbow of the quality-vs-budget curve moves with the distribution.

## What this is NOT

- Not a from-scratch attention reimplementation. The forward path of `DeepseekV3Attention` runs as-is; only the cache management changes.
- Not a training-time technique. This applies at inference. Training-time KV compression is a different toolset.
- Not an architecture replacement. This composes with sub-quadratic attention, hybrids, sparse mechanisms, etc. The point is to address the cache-bandwidth bottleneck, which is orthogonal to the choice of attention mechanism.

For background on where this sits in the broader long-context-optimization landscape, see GENOMA LABS' [research handbook on sub-quadratic attention](https://github.com/genoma-labs/subquadratic-research) (link will activate once the handbook flips public; sibling repository to this one).

## What's in this repository

```
src/
  kv_eviction_mla.py        # the patch + smoke test (277 LOC)
notebooks/
  01_smoke_test_walkthrough.md   # annotated explanation of the smoke test + memory model
docs/
  HOW_IT_WORKS.md           # architectural notes: where eviction hooks into the layer
LICENSE                     # Apache 2.0
README.md                   # this file
```

## Roadmap

- [x] H2O eviction patch for DeepseekV3Attention (transformers 4.x API)
- [x] Smoke-test on a fake-attention layer (no GPU required)
- [x] **Multi-step validation across 1,000 generation steps × 4 layers** — eviction logic verified, cache stabilizes at expected bound, no overshoot, 913 steps/sec on CPU. See [`notebooks/02_validation_results.md`](notebooks/02_validation_results.md) and [`results/validate_eviction_random_init.csv`](results/validate_eviction_random_init.csv).
- [x] **Real-weights demo on Kimi K2.6 layer 0** — loaded actual published Kimi K2.6 attention weights (101M params, all 7 weights: q_a/b_proj, q_a_layernorm, kv_a_proj_with_mqa, kv_b_proj, kv_a_layernorm, o_proj), ran a single full-prefix forward over 256 tokens on TITAN RTX, applied H2O policy. Result: kept heavy-hitters score 3.66x higher than evicted tokens on real Kimi attention distributions. See [`notebooks/03_kimi_real_weights_demo.md`](notebooks/03_kimi_real_weights_demo.md) and [`results/kimi_layer_eviction_demo.csv`](results/kimi_layer_eviction_demo.csv).
- [ ] **API port to transformers 5.x** — patch currently targets the `DynamicCache.key_cache / value_cache` list API; transformers 5.x uses `DynamicCache.layers[i]`. The eviction logic is unchanged across versions; only the cache-plumbing differs.
- [ ] **RULER 128K benchmark on a real MLA model** with eviction at 4 budget levels — planned target: Kimi K2.6 (BF16) once full-model integration via the 5.x port lands. Will publish CSV + analysis as a sibling repository (`GenomaLabs-com/h2o-eviction-ruler-bench`).
- [ ] SnapKV-style prompt-end compression composed on top of H2O eviction.
- [ ] Port to standard MHA / GQA attention classes (Llama, Qwen, Mistral, Gemma).

Pull requests for any of these are welcome. Issues, especially with reproducible failure cases, are even more welcome.

## transformers version compatibility

Currently aligned with **transformers 4.x** KV cache API. The validation script `scripts/validate_eviction_random_init.py` validates the eviction *logic* against a mock cache and runs on any Python 3.10+ environment with PyTorch — no transformers dependency. Real-model integration (`install_kv_eviction(model, ...)`) on transformers 5.x is on the roadmap; the rework is mechanical (port the cache-slicing code paths from `key_cache[i]` to `layers[i]`) but not yet shipped.

## Citation

If this implementation is useful for your work, please cite the underlying H2O paper:

```bibtex
@inproceedings{zhang2023h2o,
  title={H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models},
  author={Zhang, Zhenyu and Sheng, Ying and Zhou, Tianyi and others},
  booktitle={NeurIPS},
  year={2023}
}
```

And optionally this implementation:

```
GENOMA LABS / research. KV Cache Eviction for MLA-based Long-Context LLMs.
HuggingFace, 2026. https://huggingface.co/GenomaLabs-com/kv-cache-eviction-mla
```

## License

Apache License 2.0. See [LICENSE](LICENSE).