 Doomsdayrs
|
36d07532ef
Add missing struct annotation (#483)
|
%!s(int64=2) %!d(string=hai) anos |
 Chris Kuehl
|
6f1ee4b640
Fix crash for 65B model with pre-allocated memory (#485)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
8520fc310e
Disable BLAS altogether - the bug is not just for qunatized mat mul
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
b3f460e941
Disable BLAS branch in mul_mat - seems there is a bug
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
04c6f5ed6f
Immediately start processing the prompt before user input has been provided (#476)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
7a9b6c3a8b
Reduce memory usage and allocate enough memory for largest context (#473)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
31572d9665
Temporary bump the memory buffer size - hopefully fix issues from 483bab2e
|
%!s(int64=2) %!d(string=hai) anos |
 Gary Mulder
|
f4f5362edb
Update README.md (#444)
|
%!s(int64=2) %!d(string=hai) anos |
 rabidcopy
|
863f65e2e3
fix instruct mode (#445)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
afd220d9c6
Properly free llama_context on failure
|
%!s(int64=2) %!d(string=hai) anos |
 Cameron Kaiser
|
481044d50c
additional optimizations for POWER9 (#454)
|
%!s(int64=2) %!d(string=hai) anos |
 comex
|
563cdc391d
Support calling mlock() on loaded model data on Linux and macOS (#453)
|
%!s(int64=2) %!d(string=hai) anos |
 Luciano
|
8d4a855c24
Add embedding mode with arg flag. Currently working (#282)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
b6b268d441
Add link to Roadmap discussion
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
3cd8dde0d1
Revert "Fix memory allocation issues and seg faults"
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
4870e455b3
Fix memory allocation issues and seg faults
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
483bab2e3d
Avoid the transposed X branch in the Z = X * Y matrix multiplication (#439)
|
%!s(int64=2) %!d(string=hai) anos |
 Jed Fox
|
404e1da38e
Fix quantize script not finding models in parent directory (#428)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
4cc053b6d5
Remove oboslete command from Docker script
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
0ba5a3a9a5
Obsolete
|
%!s(int64=2) %!d(string=hai) anos |
|
rabidcopy
|
2e17dfd80a
Replace EOS with newline to prevent context/memory being flushed by EOS in interactive mode (#333)
|
%!s(int64=2) %!d(string=hai) anos |
 Timmy Knight
|
20a1a4e09c
Fix GPTQ converter (#423)
|
%!s(int64=2) %!d(string=hai) anos |
 nusu-github
|
ad072fc5ad
Generate library with CMake (#430)
|
%!s(int64=2) %!d(string=hai) anos |
 anzz1
|
ea10d3ded2
Command line args bounds checking (#424)
|
%!s(int64=2) %!d(string=hai) anos |
 Ben Siraphob
|
a18c19259a
Fix Nix build
|
%!s(int64=2) %!d(string=hai) anos |
 Stephan Walter
|
a50e39c6fe
Revert "Delete SHA256SUMS for now" (#429)
|
%!s(int64=2) %!d(string=hai) anos |
 Kerfuffle
|
a140219e81
Fix Makefile echo escape codes (by removing them). (#418)
|
%!s(int64=2) %!d(string=hai) anos |
|
Gary Mulder
|
8a3e5ef801
Move model section from issue template to README.md (#421)
|
%!s(int64=2) %!d(string=hai) anos |
|
anzz1
|
8eea5ae0e5
Delete SHA256SUMS for now (#416)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
93208cfb92
Adjust repetition penalty ..
|
%!s(int64=2) %!d(string=hai) anos |
