AlpinDale
|
e113f3e9bf
feat: spaces between special tokens (#94)
|
1 year ago |
AlpinDale
|
ae7d8df224
fix lint issues (again)
|
1 year ago |
50h100a
|
fa0ae5a2c9
feat: new mirostatv2 implementation (#96)
|
1 year ago |
AlpinDale
|
6bfe75c6e9
fix: GPTQ
|
1 year ago |
AlpinDale
|
69204736de
Revert "fix: sync CPU delay in sampler (#93)"
|
1 year ago |
AlpinDale
|
1c988a48b2
fix logging and add py.typed
|
1 year ago |
AlpinDale
|
ce66e1df56
fix: sync CPU delay in sampler (#93)
|
1 year ago |
AlpinDale
|
11c01cfd0a
fix: skip special tokens
|
1 year ago |
AlpinDale
|
41341b220a
requirements: pin pydantic version
|
1 year ago |
g4rg
|
177fad1575
chore: remove unnecessary line (#81)
|
1 year ago |
AlpinDale
|
74604eb252
fix: pylint complaints (#91)
|
1 year ago |
AlpinDale
|
efc6f7fbec
chore: reformats (#90)
|
1 year ago |
AlpinDale
|
3d72f05c7b
feat: flattened 1D tensor -> 2D tensor (#85)
|
1 year ago |
AlpinDale
|
0dcc924088
readme: add benchmarks
|
1 year ago |
AlpinDale
|
eafcd75a69
fix tests and tweak throughput benchmark
|
1 year ago |
AlpinDale
|
2460d17e54
fix positional encoding tests
|
1 year ago |
AlpinDale
|
b047197513
tests: increase tolerance for layernorm
|
1 year ago |
AlpinDale
|
9b317aa26a
feat: finish up tests and workflows (#87)
|
1 year ago |
AlpinDale
|
f73f2dd3c2
feat: add mistral support for GPTQ (#86)
|
1 year ago |
AlpinDale
|
e6be0118c9
feat: prompt logprobs and batched samplers (#77)
|
1 year ago |
city-unit
|
12e296b556
fix: update Dockerfile (#82)
|
1 year ago |
city-unit
|
27af10fd0b
chore: make entrypoint executable (#83)
|
1 year ago |
AlpinDale
|
977e8d3507
update readme with new sampling params
|
1 year ago |
AlpinDale
|
ab1ac578ba
bump version to 0.3.7-dev
|
1 year ago |
Stefan Gligorijevic
|
34c1c8c83a
feat: Enable banning tokens (#80)
|
1 year ago |
AlpinDale
|
4e71bd1d12
feat: add PagedAttention V2 kernels (#76)
|
1 year ago |
50h100a
|
d0eadd4dbd
Added `min_tokens` and reimplemented `ignore_eos` using a new logit processor (#70)
|
1 year ago |
AlpinDale
|
04a27c6aeb
fix: revert mirostat v2 (#79)
|
1 year ago |
AlpinDale
|
9c353a0e02
fix: unnecessary import
|
1 year ago |
AlpinDale
|
ce5e2332ea
fix: launch AWQ kernels on the current CUDAStream (#75)
|
1 year ago |