sail/longspec-Llama-3-8B-Instruct-262k

Model

0

stars

4

commits

2

repos using this model

1

linked in READMEs

Jul 27, 2025

updated

endpoints_compatible

llama

safetensors

text-generation

text-generation-inference

transformers

README

This repository contains the LongSpec model described in LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification.

Code: https://github.com/sail-sg/LongSpec

Contributors

3 commits

1 commits

Similar repos

sail/longspec-longchat-13b-16k

0

sail/longspec-longchat-7b-v1.5-32k

0

sail/longspec-vicuna-7b-v1.5-16k

0

sail/longspec-vicuna-13b-v1.5-16k

0

sail/longspec-QwQ-32B-Preview

0

GSAI-ML/LLaDA-8B-Instruct

363

GSAI-ML/LLaDA-8B-Base

102

lmsys/longchat-7b-v1.5-32k

61

Used in code

sail-sg/LongSpec

[ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and…

86

tranphuc15122004/fast_infer_for_text_sum

0

Linked in READMEs

sail-sg/LongSpec

[ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and…

86

sail/longspec-Llama-3-8B-Instruct-262k

Model

0

stars

4

commits

2

repos using this model

1

linked in READMEs

Jul 27, 2025

updated

endpoints_compatible

llama

safetensors

text-generation

text-generation-inference

transformers

README

This repository contains the LongSpec model described in LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification.

Code: https://github.com/sail-sg/LongSpec

Similar repos

sail/longspec-longchat-13b-16k

0

sail/longspec-longchat-7b-v1.5-32k

0

sail/longspec-vicuna-7b-v1.5-16k

0

sail/longspec-vicuna-13b-v1.5-16k

0

sail/longspec-QwQ-32B-Preview

0

GSAI-ML/LLaDA-8B-Instruct

363

GSAI-ML/LLaDA-8B-Base

102

lmsys/longchat-7b-v1.5-32k

61

Used in code

sail-sg/LongSpec

[ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and…

86

tranphuc15122004/fast_infer_for_text_sum

0

Linked in READMEs

sail-sg/LongSpec

[ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and…

86

Contributors

3 commits

1 commits