issues
search
FasterDecoding
/
REST
REST: Retrieval-Based Speculative Decoding, NAACL 2024
Apache License 2.0
166
stars
10
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Tensor parallelism
#21
lethean1
opened
5 days ago
0
about retrieve sequence length
#20
Siegfried-qgf
opened
2 weeks ago
0
OSError: failed to fill whole buffer
#19
Siegfried-qgf
opened
3 weeks ago
5
How to adjust the maximum token lengths when drafting?
#18
zomss
opened
1 month ago
3
LLama3 8B is not supported
#17
liranringel
opened
3 months ago
2
If I want to change REST code to support multi-batch inference, what needs to be changed?
#16
yangbohust
opened
4 months ago
0
How to support the `repetition_penalty` parameter?
#15
yangbohust
opened
4 months ago
0
Segmentation Fault when calling libsais_int
#14
julianmukaj
opened
5 months ago
0
ValueError: draft_choices was not cut enough / draft_len should not exceed 65
#13
yangbohust
opened
5 months ago
3
What are the meanings of each parameter of the reader.search() function? k\choices\long
#12
yangbohust
opened
5 months ago
9
pyo3_runtime.PanicException: called `Result::unwrap()` on an `Err` value: RuntimeError(StackOverflow)
#11
yangbohust
closed
5 months ago
1
Gracefully handles when draft_choices is not cut enough
#10
wangpatrick57
closed
5 months ago
0
codellama-7b working on GPUs with 24GB memory
#9
wangpatrick57
closed
6 months ago
0
Ngram build cli
#8
wangpatrick57
closed
6 months ago
0
Small QOL changes
#7
wangpatrick57
closed
6 months ago
2
Questions about past_key_values_data
#6
reflectionie
closed
6 months ago
2
What is the acceptance procedure in REST?
#5
jivanph
closed
7 months ago
3
Cannot install the .whl
#4
hasuoshenyun
closed
7 months ago
2
Incompatibility issues with llama-7b model
#3
preminstrel
closed
8 months ago
6
Could REST support beam search sampling policy?
#2
leiwen83
closed
6 months ago
1
DraftRetriever wheels file missing
#1
drdsgvo
closed
11 months ago
2