huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-22 23:42:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
b1077b077c
text-generation-inference/server/text_generation_server/utils
History
Daniël de Kok 26460f053d Add support for repacking AWQ weights for GPTQ-Marlin (#2278) 
* Add support for repacking AWQ weights for GPTQ-Marlin

So far we couldn't support AWQ because virtually all AWQ models use
symmetric quantization, which GPTQ-Marlin did not suppors. GPTQ-Marlin
has recently added support AWQ repacking and AWQ asymmetric quantization
(zero_point=True).

This change updates all GPTQ-Marlin kernels from upstream and wires up
AWQ support. For now enabling AWQ using Marlin requires running TGI with
`--quantize gptq`.

* Enable Marlin for supported AWQ configurations by default

This makes the AWQ -> GPTQ repack test redundant, since we are now
testing this with the regular AWQ test.
2024-09-25 05:31:31 +00:00
..
merges Enable multiple LoRa adapters (#2010) 2024-09-24 03:55:04 +00:00
__init__.py Aligin the source code with main branch 2.0.4 2024-09-24 03:06:55 +00:00
adapter.py Enable multiple LoRa adapters (#2010) 2024-09-24 03:55:04 +00:00
chunks.py server: use chunked inputs 2024-09-24 03:42:29 +00:00
convert.py Force weights_only (before fully breaking pickle files anyway). (#1710) 2024-04-25 15:10:53 +03:00
dist.py feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248) 2024-09-25 05:30:41 +00:00
hub.py Enable multiple LoRa adapters (#2010) 2024-09-24 03:55:04 +00:00
import_utils.py refine get xpu free memory/enable Qwen2/gemma2/gemma/phi in intel platform (#2132) 2024-09-24 03:57:32 +00:00
log.py feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248) 2024-09-25 05:30:41 +00:00
logits_process.py Aligin the source code with main branch 2.0.4 2024-09-24 03:06:55 +00:00
peft.py Enable multiple LoRa adapters (#2010) 2024-09-24 03:55:04 +00:00
quantization.py Add support for repacking AWQ weights for GPTQ-Marlin (#2278) 2024-09-25 05:31:31 +00:00
segments.py Enable multiple LoRa adapters (#2010) 2024-09-24 03:55:04 +00:00
sgmv.py Enable multiple LoRa adapters (#2010) 2024-09-24 03:55:04 +00:00
speculate.py chore: formatting 2024-04-18 16:26:00 +03:00
tokens.py Aligin the source code with main branch 2.0.4 2024-09-24 03:06:55 +00:00
watermark.py Aligin the source code with main branch 2.0.4 2024-09-24 03:06:55 +00:00
weights.py fix(server): fix fp8 weight loading (#2268) 2024-09-25 05:31:08 +00:00