 Mehdi Z.
|
41adb27e76
sampler: fix typos in DRY (#857)
|
1 hónapja |
 AlpinDale
|
c6e0ae0515
sampler: apply sequence breakers per-sequence in a batch
|
1 hónapja |
|
AlpinDale
|
44eb7df8c3
misc: trailing whitespace
|
1 hónapja |
|
AlpinDale
|
f28847b38b
sampler: optimize DRY performance using z-algorithm
|
1 hónapja |
 AlpinDale
|
2150bb5019
sampler: add range parameter for DRY (#855)
|
1 hónapja |
|
AlpinDale
|
72c505ad84
sampler: fix dry concurrency issue (#852)
|
1 hónapja |
 Selali
|
14ac216498
sampler: add output_tokens to DRY sampler (#849)
|
1 hónapja |
 Luke Harold Miles
|
d486d7ac01
docs: add linux arm64/aarch64/GH200 installation tips (#851)
|
1 hónapja |
|
AlpinDale
|
d2971a6831
ci: bump version to 0.6.4 (#845)
|
1 hónapja |
|
AlpinDale
|
538471f76e
chore: bump mistral_common to 1.5.0 (#844)
|
1 hónapja |
|
AlpinDale
|
483c9e6e59
fix: disable awq_marlin override for awq models (#843)
|
1 hónapja |
|
AlpinDale
|
dfa34d1b24
feat: add sampler_priorty (#837)
|
1 hónapja |
|
AlpinDale
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 hónapja |
|
AlpinDale
|
563e8f7ac8
fix: latency and serving benchmarks (#841)
|
1 hónapja |
|
AlpinDale
|
7c7ec12f36
chore: refactor executor classes for easier inheritance (#840)
|
1 hónapja |
|
AlpinDale
|
16b587c104
fix: hidden states handling in batch expansion for spec decoding (#839)
|
1 hónapja |
|
AlpinDale
|
60f7b828d5
feat: add skew sampling (#834)
|
1 hónapja |
|
AlpinDale
|
ba9d8f631a
feat: add no_repeat_ngram sampler (#832)
|
1 hónapja |
|
Selali
|
4c4a365f77
feat: Add DRY (Don't Repeat Yourself) sampling (#827)
|
1 hónapja |
|
AlpinDale
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 hónapja |
|
AlpinDale
|
2242cb25dc
fix: unbound tokenizer error
|
1 hónapja |
|
AlpinDale
|
3d83e64f8e
feat: add metrics for prefix cache hit rate (#829)
|
1 hónapja |
|
AlpinDale
|
22425b689d
fix: XPU build
|
1 hónapja |
|
AlpinDale
|
bfc8988116
feat: add cuda sampling kernels for top_k and top_p (#828)
|
1 hónapja |
|
AlpinDale
|
22427602eb
feat: add top-nsigma sampling method
|
1 hónapja |
|
AlpinDale
|
22429e4a10
fix: sampler test with new transformers version
|
1 hónapja |
|
AlpinDale
|
2f61644f6e
SPMD optimizations (#824)
|
1 hónapja |
|
AlpinDale
|
32a37e8107
tests: partially fix tensorizer and logprobs tests
|
1 hónapja |
|
AlpinDale
|
7f1c9af5e2
fix: fp8 quant test
|
1 hónapja |
|
AlpinDale
|
173ac23399
fix: experts int8 quant test
|
1 hónapja |
