Nicolas Patry 5bd2ab6583 feat(server): Support for env value for GPTQ_BITS and GPTQ_GROUPSIZE. (#580) ... # What does this PR do? Some models are already converted, and do not have those values in the file, this enables users to use them with less friction. Went for pure env based because adding flags would end up (imo) very tedious to maintain. There's a lot of sanitation to do: those flags would be errors if not used in conjuction with `--quantize gptq`. Then the flags need to exist in the launcher and the server passing them all throughout all function calls. This PR is intended as an easy escape hatch, not the defacto method to use gptq in TGI. Fixes #500		2023-07-12 10:00:02 +02:00
..
gptq	feat(server): Add inference support for GPTQ (llama + falcon tested) + Quantization script (#438)	2023-06-26 12:27:01 +02:00
__init__.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
convert.py	fix(server): harden the weights choice to save on disk. (#561)	2023-07-07 14:50:12 +02:00
dist.py	fix(server): Do not init process group if already initialized (#388)	2023-06-26 12:32:54 +02:00
hub.py	feat(server): Adding new ignore_rule for conversion. (#485)	2023-06-23 12:41:13 +02:00
layers.py	feat(server): use latest flash attention commit (#543)	2023-07-04 20:23:55 +02:00
logits_process.py	fix(server): avoid errors for very small top_p values (#544)	2023-07-04 20:11:33 +02:00
tokens.py	feat(server): add paged attention to flash models (#516)	2023-06-30 19:09:59 +02:00
watermark.py	fix(server): fix flash-neox scores warping (#137)	2023-03-24 18:21:41 +01:00
weights.py	feat(server): Support for env value for GPTQ_BITS and GPTQ_GROUPSIZE. (#580)	2023-07-12 10:00:02 +02:00