issues
search
RWKV
/
rwkv.cpp
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
MIT License
1.37k
stars
90
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
file parsing and memory usage optimization
#74
LoganDark
closed
1 year ago
26
Flush output every token in generate_completions.py
#73
LoganDark
closed
1 year ago
0
Silence PyTorch warnings by using untyped storage
#72
LoganDark
closed
1 year ago
0
last second move things over in the error enum
#71
LoganDark
closed
1 year ago
0
Switch to fstat64
#70
LoganDark
closed
1 year ago
2
Move graph building into its own function
#69
LoganDark
closed
1 year ago
3
Add rwkv_set_print_errors and rwkv_get_last_error
#68
LoganDark
closed
1 year ago
25
Slow Inference
#67
xdevfaheem
closed
1 year ago
3
How to increase state size?
#66
richardburleigh
closed
1 year ago
2
Feature add cublas support
#65
yorkzero831
closed
1 year ago
27
UnExpected Outputs
#64
xdevfaheem
closed
1 year ago
3
Get error status and message without stderr
#63
LoganDark
closed
1 year ago
8
Add CuBLAS support
#62
yorkzero831
closed
1 year ago
1
Basic Samplers?
#61
ArEnSc
closed
11 months ago
4
Is it possible to implement the seq mode for loading prompt?
#60
L-M-Sherlock
closed
1 year ago
1
Apple Silicon : mach-o file, but is an incompatible architecture (have 'x86_64', need 'arm64')
#59
mozzipa
opened
1 year ago
3
Fix encoding issue when loading prompt data
#58
baiyuanneko
closed
1 year ago
0
How can i build android rwkv.cpp?
#57
xiaol
closed
1 year ago
2
Blas-like Prompt Parallelization? (sequence processing mode)
#55
paryska99
closed
1 year ago
1
Library Fails to Build
#54
wereretot
closed
1 year ago
1
Python type hint cannot work: A: list[int]=[] when run chat_with_bot.py
#53
Oshibuki
closed
1 year ago
3
Various improvements
#52
saharNooby
closed
1 year ago
0
WARNING: Unused parameter in LoRA state dict
#51
iclgg
closed
1 year ago
6
Add MMAP support
#50
PicoCreator
opened
1 year ago
2
Adding rwkv_eval_array operation
#49
PicoCreator
closed
1 year ago
3
AssertionError: xxxxxxxxx.bin is not a file
#48
s567901
closed
1 year ago
2
Various improvements
#47
saharNooby
closed
1 year ago
0
"Unsupported quantization type" when quantizing model
#46
BuilderGuy1
closed
1 year ago
2
Use main ggml repo instead of fork
#45
saharNooby
closed
1 year ago
0
Add support for Q5_0, Q5_1 and Q8_0 formats; remove Q4_1_O format
#44
saharNooby
closed
1 year ago
0
Illegal instruction (Intel N4200, Linux Ubuntu Jaunty)
#43
radscience
opened
1 year ago
4
Inference binary
#42
drdaffey
closed
1 year ago
1
Cmake Error
#41
QuanBit
opened
1 year ago
2
fraction of my custom stuff rebased onto #21
#40
iacore
closed
11 months ago
1
Improve chat_with_bot.py script
#39
saharNooby
closed
1 year ago
0
Sync ggml with upstream
#38
saharNooby
closed
1 year ago
0
punish repetitions & break if END_OF_TEXT & decouple prompts from chat script
#37
L-M-Sherlock
closed
1 year ago
5
chat_with_bot will stop when '\n' in response.
#36
asukaminato0721
closed
1 year ago
1
Consider uploading some quantized checkpoints to hugginface
#35
Calandiel
opened
1 year ago
2
Improve the prompt & fix chinese display issue & support commands
#34
L-M-Sherlock
closed
1 year ago
4
Add robust automatic testing
#33
saharNooby
closed
1 year ago
0
(Ubuntu x86_64) Segmentation Fault Running Q4_1_O Model
#32
cryscan
closed
1 year ago
12
a bunch of features
#30
iacore
closed
1 year ago
8
Mac Build stops with Errors
#29
BuilderGuy1
closed
1 year ago
3
Move ggml to submodule
#28
saharNooby
closed
1 year ago
1
Can we use Q4_1 for some of the matrices?
#27
BlinkDL
closed
1 year ago
2
Code difference is getting more between ggml and rwkv.cpp
#25
yorkzero831
closed
1 year ago
4
Crash on an `endbr64` instruction.
#24
RnMss
opened
1 year ago
8
Lanchain.js integration
#23
ansarizafar
opened
1 year ago
4
chat_with_bot.py not work well with Raven v8
#22
zklhp
closed
1 year ago
3
Previous
Next