Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,179 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
+base_model: Qwen/Qwen3.6-27B
+base_model_relation: quantized
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- qwen3_5
+- autoround
+- int4
+- w4g128
+- w4a16
+- quantization
+- vllm
+- multimodal
+- mtp
+- speculative-decoding
+---
+# Qwen3.6-27B INT4 AutoRound (Best Recipe)
+
+A **W4A16 (INT4 weight, FP16 activation) quantization** of [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B), produced with [Intel's AutoRound](https://github.com/intel/auto-round).
+
+> **Key difference from other AutoRound quants of this model:** This was quantized using the **`auto-round-best` preset** — 1000 iterations and 512 calibration samples instead of the standard 200/128. This preset runs ~4–5× slower but achieves the best possible accuracy at INT4, as it performs a more thorough weight rounding optimization. MTP (speculative decoding) and image/vision inputs work out of the box with no post-processing required.
+
+## TL;DR
+
+- **Base**: Qwen3.6-27B (27B dense VLM)
+- **Quant**: INT4 W4A16, group_size 128, symmetric
+- **Tool**: `auto-round-best` (1000 iters, 512 samples, torch.compile)
+- **Size**: ~18 GB (down from ~54 GB BF16) — **3× reduction**
+- **MTP**: Native Multi-Token Prediction head preserved in BF16 — enables **native speculative decoding** in vLLM (~85–90% draft acceptance, ~2× throughput)
+- **Vision**: Image inputs work via the MoonViT encoder (weights kept at original BF16/FP16 precision)
+
+## Quick inference with vLLM (with MTP speculative decoding)
+
+Requires vLLM v0.19.1+ with Qwen3_5 MTP support. Set the following environment variables before starting:
+
+```bash
+export VLLM_USE_FLASHINFER_SAMPLER=1
+export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+export VLLM_FLOAT32_MATMUL_PRECISION=high
+export PYTORCH_CUDA_ALLOC_CONF="expandable_segments:True,max_split_size_mb:512"
+export VLLM_NO_USAGE_STATS=1
+export VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=1
+export VLLM_MARLIN_USE_ATOMIC_ADD=1
+export OMP_NUM_THREADS=1
+export CUDA_DEVICE_MAX_CONNECTIONS=8
+export NCCL_CUMEM_ENABLE=0
+export NCCL_P2P_DISABLE=1
+```
+
+```bash
+vllm serve webhie/Qwen3.6-27B-int4-AutoRound \
+  --served-model-name qwen3.6-27b \
+  --host 0.0.0.0 --port 11434 \
+  --trust-remote-code \
+  --dtype auto \
+  --quantization auto_round \
+  --max-model-len 200704 \
+  --gpu-memory-utilization 0.92 \
+  --max-num-seqs 4 \
+  --kv-cache-dtype fp8_e4m3 \
+  --attention-backend flashinfer \
+  --performance-mode throughput \
+  --max-num-batched-tokens 2048 \
+  --enable-chunked-prefill \
+  --enable-auto-tool-choice \
+  --tool-call-parser qwen3_coder \
+  --reasoning-parser qwen3 \
+  --default-chat-template-kwargs '{"preserve_thinking":true}' \
+  --override-generation-config '{"temperature":0.6,"top_p":0.95,"top_k":20,"min_p":0.0,"presence_penalty":0.0,"repetition_penalty":1.0}' \
+  --enable-prompt-tokens-details \
+  --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
+```
+
+Remove `--speculative-config` to disable MTP speculative decoding. See the [vllm-blackwell-guide](https://github.com/lastloop-ai/vllm-blackwell-guide) repo for a full Docker Compose setup with all env vars pre-configured.
+
+### OpenAI-compatible request
+
+```python
+from openai import OpenAI
+client = OpenAI(base_url="http://localhost:11434/v1", api_key="EMPTY")
+r = client.chat.completions.create(
+    model="qwen3.6-27b",
+    messages=[{"role": "user", "content": "Write a quicksort in Python."}],
+    max_tokens=512,
+)
+print(r.choices[0].message.content)
+```
+
+### Transformers (no spec decoding)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+m = AutoModelForCausalLM.from_pretrained(
+    "webhie/Qwen3.6-27B-int4-AutoRound",
+    trust_remote_code=True,
+    device_map="auto",
+)
+tok = AutoTokenizer.from_pretrained("webhie/Qwen3.6-27B-int4-AutoRound")
+msg = [{"role": "user", "content": "Explain quantum computing briefly."}]
+ids = tok.apply_chat_template(msg, add_generation_prompt=True, return_tensors="pt").to(m.device)
+print(tok.decode(m.generate(ids, max_new_tokens=256)[0]))
+```
+
+## Quantization details
+
+| Field | Value |
+|---|---|
+| Base | `Qwen/Qwen3.6-27B` |
+| Method | AutoRound (`intel/auto-round`), **best recipe** |
+| Scheme | W4A16 (4-bit weights, FP16 activations) |
+| Bits | 4 |
+| Group size | 128 |
+| Symmetric | yes |
+| Packing format | `auto_round:auto_gptq` |
+| Unquantized layers | `linear_attn.in_proj_a/b`, all LayerNorms, RMSNorms, router gates |
+| Calibration samples | 512 |
+| Iterations | 1000 |
+| torch.compile | enabled |
+| GPU used for quant | 1× RTX 5090 (32 GB, SM120), `low_gpu_mem_usage=True` |
+
+### Unquantized layers — why
+
+- **`linear_attn.in_proj_a/b`**: low-rank projections in Qwen3.6's Gated DeltaNet whose shapes aren't divisible by 32 (group_size), so AutoRound skips them automatically. Tiny fraction of total parameters.
+- **Norms, routers**: precision-sensitive and very small — kept at full precision.
+
+## Performance
+
+Benchmarked on **1× RTX 5090 (32 GB)** with vLLM + FP8 KV cache + MTP n=3:
+
+| Config | Throughput |
+|---|---:|
+| vLLM + MTP n=3 | **~150 tok/s** |
+| vLLM (MTP disabled) | **~70 tok/s** |
+
+The ~2× speedup comes from ~85–90% draft acceptance via MTP speculative decoding with `num_speculative_tokens: 3`.
+
+## Reproduction
+
+```bash
+pip install auto-round
+auto-round-best \
+  --model Qwen/Qwen3.6-27B \
+  --scheme W4A16 \
+  --format auto_round \
+  --output_dir Qwen3.6-27B-int4-AutoRound \
+  --enable_torch_compile \
+  --low_gpu_mem_usage \
+  --device_map 0
+```
+
+No post-processing needed — MTP and image inputs work out of the box.
+
+## Acknowledgements
+
+- [Alibaba / Qwen team](https://huggingface.co/Qwen) for the base [Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) model
+- [Intel AutoRound](https://github.com/intel/auto-round) team for the quantization framework
+- [Lorbus](https://huggingface.co/Lorbus) for the original AutoRound quant of this model that inspired this release
+- [@eugr](https://github.com/eugr) for the [spark-vllm-docker](https://github.com/eugr/spark-vllm-docker) fork and TurboQuant KV cache work
+- [vLLM project](https://github.com/vllm-project/vllm) for the inference engine and Qwen3_5 MTP support
+
+## License
+
+Apache 2.0 — same as [Qwen3.6-27B base](https://huggingface.co/Qwen/Qwen3.6-27B).
+
+## Citation
+
+If you use this quant, please cite the original Qwen3.6 release (see base model card) and the AutoRound paper:
+
+```bibtex
+@article{cheng2023autoround,
+  title   = {Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs},
+  author  = {Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi},
+  journal = {arXiv preprint arXiv:2309.05516},
+  year    = {2023}
+}
+```