 AlpinDale
|
4b80b42362
fix: memory leaks due to nccl cuda graphs (#275)
|
vor 11 Monaten |
|
AlpinDale
|
842912d022
feat: on-the-fly gguf conversion (#250)
|
vor 1 Jahr |
|
AlpinDale
|
d2db4143fa
feat: add grafana for metrics (#240)
|
vor 1 Jahr |
|
AlpinDale
|
bb158b6282
fix: bump torch to 2.2.0 (#234)
|
vor 1 Jahr |
|
AlpinDale
|
1c46fa31ad
feat: add quadratic sampling (#233)
|
vor 1 Jahr |
 AlpinDale
|
f0dacc17dd
fix: remove fast-hadamard-transform in requirements
|
vor 1 Jahr |
|
AlpinDale
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
vor 1 Jahr |
|
AlpinDale
|
0adab894fe
feat: grammar support (#206)
|
vor 1 Jahr |
|
AlpinDale
|
339c6aec53
chore: bump ray version
|
vor 1 Jahr |
|
AlpinDale
|
641bb0f6e9
feat: add custom allreduce kernels (#224)
|
vor 1 Jahr |
|
AlpinDale
|
fe70c6e8d5
feat: bump cuda and pytorch (#205)
|
vor 1 Jahr |
|
AlpinDale
|
7e72ce0a73
feat: mixtral tensor parallelism (#193)
|
vor 1 Jahr |
|
AlpinDale
|
7d91e9e0f2
feat: CUDA graphs (#172)
|
vor 1 Jahr |
|
AlpinDale
|
b9df8734d1
remove megablocks as a dependency
|
vor 1 Jahr |
|
AlpinDale
|
23a54389c8
bump torch
|
vor 1 Jahr |
|
AlpinDale
|
2755a48d51
merge dev branch into main (#153)
|
vor 1 Jahr |
|
AlpinDale
|
887e03669a
feat: add exllamav2 for GPTQ (#99)
|
vor 1 Jahr |
|
AlpinDale
|
161a69d2e0
Update requirements.txt
|
vor 1 Jahr |
|
AlpinDale
|
41341b220a
requirements: pin pydantic version
|
vor 1 Jahr |
|
AlpinDale
|
9b317aa26a
feat: finish up tests and workflows (#87)
|
vor 1 Jahr |
|
AlpinDale
|
28db67fd78
fix: mistral support
|
vor 1 Jahr |
 LitreallyNone
|
b526a7b3bc
Update requirements.txt (#58)
|
vor 1 Jahr |
|
AlpinDale
|
1e7d28f96f
fix: torch version mismatch (#43)
|
vor 1 Jahr |
|
AlpinDale
|
da79f86e52
bump transformers and xformers versions
|
vor 1 Jahr |
|
AlpinDale
|
2148f4be91
update requirements
|
vor 1 Jahr |
|
AlpinDale
|
aba8b0b17a
add rope theta support and bump transformers
|
vor 1 Jahr |
|
AlpinDale
|
c687430ce7
bump xformers and clean up leftover code
|
vor 1 Jahr |
|
AlpinDale
|
acbf49ef89
feat: refactor scheduler
|
vor 1 Jahr |
|
AlpinDale
|
10334ebd7c
requirements: stricter version for fschat
|
vor 1 Jahr |
|
AlpinDale
|
592ee204a6
fix: ray depends on pyarrow
|
vor 1 Jahr |
