Jackrong/Qwopus3.6-27B-v2-FP8

Update chat template tool-call serialization

Highlight MTP Q8 speed column

Refine FP8 speed comparison table

Add FP8 output speed comparison report

Clean vLLM FP8 README compatibility section

Clean up model card: remove garbage text history and Verified Notes column

Replace with fixed vLLM FP8 model (7-shard, no garbled output)

Fix README HTML rendering for vLLM FP8 section

Refine vLLM FP8 compatibility notes

Update README with vLLM FP8 compatibility fix

Upload README.md with huggingface_hub

Remove model.safetensors.index.json.gate-fp8.bak

Remove model.safetensors.index.json.bak

Remove fp8_mtp_30q_results.json

Upload Qwopus3.6-27B-v2 FP8

initial commit