TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
Paper
•
2410.05076
•
Published
•
8
Zhihao Zhang
JackFram
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 months ago
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent
Sparse Attention
commented on
a paper
4 months ago
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent
Sparse Attention
authored
a paper
4 months ago
SpecInfer: Accelerating Generative LLM Serving with Speculative
Inference and Token Tree Verification
Organizations
JackFram's activity
upvoted
a
paper
2 months ago
commented
a
paper
4 months ago
authored
a
paper
4 months ago
updated
a
model
8 months ago
liked
a
model
11 months ago
Could you add license information of this model?
2
#7 opened over 1 year ago
by
gombaal
Fine Tuning
1
#13 opened about 1 year ago
by
Jenish-23
updated
a
model
about 1 year ago
align_with_llama2
#12 opened about 1 year ago
by
goliaro
Fix bos_token_id to match BOS from tokenizer.model file
#11 opened about 1 year ago
by
goliaro
updated
a
model
about 1 year ago
Fix bos_token_id to match BOS from tokenizer.model file
#1 opened about 1 year ago
by
goliaro
Update special_tokens_map.json
#4 opened over 1 year ago
by
Xenova
Update special_tokens_map.json
1
#10 opened over 1 year ago
by
ArthurZ
Fix tokenizer_config.json
3
#9 opened over 1 year ago
by
Xenova
Adding `safetensors` variant of this model
#8 opened over 1 year ago
by
SFconvertbot