| .. |
|
layers
|
f663d3fccc
Merge pull request #397 from 50h100a/pr_samplerasserts
|
11 ماه پیش |
|
megatron
|
29c241c115
fix: explicitly disallow installation on non-linux platforms (#373)
|
11 ماه پیش |
|
models
|
72cd8494aa
feat: mistral neuron support (#368)
|
11 ماه پیش |
|
__init__.py
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
1 سال پیش |
|
hf_downloader.py
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
11 ماه پیش |
|
loader.py
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
11 ماه پیش |
|
metadata.py
|
78d66f16d1
Chunked Prefill Part 1 (#384)
|
11 ماه پیش |
|
neuron_loader.py
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
11 ماه پیش |
|
outlines_decoding.py
|
0b35176089
feat: add context-free grammars (#376)
|
11 ماه پیش |
|
outlines_logits_processors.py
|
0b35176089
feat: add context-free grammars (#376)
|
11 ماه پیش |
|
sampling_metadata.py
|
0634b8a3a6
fix memory pinning conditional
|
11 ماه پیش |
|
utils.py
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
11 ماه پیش |
50h100a
f663d3fccc
Merge pull request #397 from 50h100a/pr_samplerasserts