kv-landlords / vllm /docs /features /speculative_decoding

Ctrl+K

Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source

6e668dc verified about 2 months ago

README.md

11.1 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
draft_model.md

2.35 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
eagle.md

2.38 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
extract_hidden_states.md

3.56 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
mlp.md

2.4 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
mtp.md

2.45 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
n_gram.md

803 Bytes
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
parallel_draft_model.md

1.25 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
speculators.md

2.89 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago
suffix.md

1.8 kB
Upload kv-quant (INT4/NVFP4 KIVI) work + vLLM fork source about 2 months ago