text-generation-inference/server/text_generation_server
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
..
adapters Enable multiple LoRa adapters (#2010) 2024-09-24 03:55:04 +00:00
layers Add support for repacking AWQ weights for GPTQ-Marlin (#2278) 2024-09-25 05:31:31 +00:00
models Fixing mistral nemo. (#2276) 2024-09-25 05:31:30 +00:00
pb chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
utils Add support for repacking AWQ weights for GPTQ-Marlin (#2278) 2024-09-25 05:31:31 +00:00
__init__.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00
cache.py fix(server): decrease memory fragmentation (#557) 2023-07-06 14:28:33 +02:00
cli.py feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248) 2024-09-25 05:30:41 +00:00
interceptor.py Aligin the source code with main branch 2.0.4 2024-09-24 03:06:55 +00:00
server.py Enable multiple LoRa adapters (#2010) 2024-09-24 03:55:04 +00:00
tracing.py Add OTLP Service Name Environment Variable (#2076) 2024-09-24 03:51:26 +00:00