Daniël de Kok 5726a9ca81 Move to moe-kernels package and switch to common MoE layer ... This change introduces the new `moe-kernels` package: - Add `moe-kernels` as a dependency. - Introduce a `SparseMoELayer` module that can be used by MoE models. - Port over Mixtral and Deepseek.		2024-09-16 10:57:44 +00:00
..
merges	feat: add ruff and resolve issue (#2262)	2024-07-26 10:29:09 -04:00
__init__.py	…
adapter.py	fix: pass missing revision arg for lora adapter when loading multiple… (#2510)	2024-09-12 17:04:52 +02:00
chunks.py	…
convert.py	…
dist.py	feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248)	2024-07-20 19:02:04 +02:00
hub.py	Enable multiple LoRa adapters (#2010)	2024-06-25 14:46:27 -04:00
import_utils.py	Pr 2337 ci branch (#2379)	2024-08-08 12:30:29 -04:00
log.py	feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248)	2024-07-20 19:02:04 +02:00
logits_process.py	patch-error-on-invalid-grammar (#2282)	2024-07-29 10:09:25 -04:00
peft.py	feat: add ruff and resolve issue (#2262)	2024-07-26 10:29:09 -04:00
quantization.py	Handle GPTQ-Marlin loading in `GPTQMarlinWeightLoader` (#2300)	2024-07-31 13:08:41 +02:00
segments.py	Enable multiple LoRa adapters (#2010)	2024-06-25 14:46:27 -04:00
sgmv.py	fix: allocate tmp based on sgmv kernel if available (#2345)	2024-08-12 17:24:32 +02:00
speculate.py	…
tokens.py	feat: add ruff and resolve issue (#2262)	2024-07-26 10:29:09 -04:00
watermark.py	…
weights.py	Move to moe-kernels package and switch to common MoE layer	2024-09-16 10:57:44 +00:00