| .. |
|
fused_moe
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
3 mesi fa |
|
mamba
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
ops
|
8a71788372
Add OLMoE (#772)
|
2 mesi fa |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 anno fa |
|
activation.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
layernorm.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
linear.py
|
e182d00256
feat: AWQ quantization for InternVL (#867)
|
1 mese fa |
|
logits_processor.py
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
4 mesi fa |
|
pooler.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
rejection_sampler.py
|
e3a53712f2
fix: mlpspeculator with padded vocab (#669)
|
4 mesi fa |
|
rotary_embedding.py
|
4434c4db84
chore: refactor llama3 rope (#748)
|
3 mesi fa |
|
sampler.py
|
ef99a567b6
fix: temp_last warning being repeated for every output token (#869)
|
1 mese fa |
|
spec_decode_base_sampler.py
|
09b82f9963
feat: Add support for GPU device selection in SpecDecodeBaseSampler (#629)
|
4 mesi fa |
|
typical_acceptance_sampler.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
vocab_parallel_embedding.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
AlpinDale
ef99a567b6
fix: temp_last warning being repeated for every output token (#869)