AlpinDale
|
641bb0f6e9
feat: add custom allreduce kernels (#224)
|
11 months ago |
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
11 months ago |
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 months ago |
AlpinDale
|
fe70c6e8d5
feat: bump cuda and pytorch (#205)
|
1 year ago |
AlpinDale
|
7e72ce0a73
feat: mixtral tensor parallelism (#193)
|
1 year ago |
AlpinDale
|
801eda0b7a
feat: support GPTQ 2, 3, and 8bit quants (#181)
|
1 year ago |
AlpinDale
|
68c2083adb
fix includes in wheel
|
1 year ago |
AlpinDale
|
62b2c4119d
feat: re-write GPTQ and refactor exllama kernels (#152)
|
1 year ago |
AlpinDale
|
1334a833a4
feat: AMD ROCm support (#95)
|
1 year ago |
AlpinDale
|
2b1ba581f9
feat: re-implement GPTQ (#141)
|
1 year ago |
AlpinDale
|
8223f85c1b
feat: SqueezeLLM support (#140)
|
1 year ago |
AlpinDale
|
1aab8a7d6f
feat: speedup compilation times by 3x (#130)
|
1 year ago |
AlpinDale
|
e7b6a2d5a0
chore: tensor parallel refactors part 2 (#116)
|
1 year ago |
AlpinDale
|
887e03669a
feat: add exllamav2 for GPTQ (#99)
|
1 year ago |
AlpinDale
|
1c988a48b2
fix logging and add py.typed
|
1 year ago |
AlpinDale
|
561773dec8
fix: hopefully fixes github actions
|
1 year ago |
AlpinDale
|
0495c50a3e
GPTQ+exllama support (#21)
|
1 year ago |
AlpinDale
|
99657d444b
fix: incorrect cc
|
1 year ago |
AlpinDale
|
e8c0d863d7
update setuptools to compile new kernels
|
1 year ago |
AlpinDale
|
d9c1d4f6e5
add awq support
|
1 year ago |
AlpinDale
|
39beed0b87
Revert "Refactor AWQ support."
|
1 year ago |
AlpinDale
|
d09e27f5d4
Refactor AWQ support.
|
1 year ago |
AlpinDale
|
c318602c42
update setuptools
|
1 year ago |
AlpinDale
|
76b2e4a445
Merge dev branch into main (#7)
|
1 year ago |
AlpinDale
|
908091008e
readme: typo
|
1 year ago |
AlpinDale
|
d8105984b8
fix: update setuptools again
|
1 year ago |
AlpinDale
|
15a3e6c377
fix: setuptools fix
|
1 year ago |
AlpinDale
|
682c791295
chore: add examples to the setuptools exclusions
|
1 year ago |
AlpinDale
|
b6d7bbbd0d
feat: add setuptools for the project
|
1 year ago |