Daniël de Kok 0f346a3296 Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels (#2688) ... * Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels Performance and accuracy of these kernels are on par (tested with Llama 70B and 405B). Removes a dependency and resolves some stability issues we have been seeing. * Update test snapshots		2024-10-25 16:40:47 +02:00
..
adapters	feat: add ruff and resolve issue (#2262)	2024-07-26 10:29:09 -04:00
layers	Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels (#2688)	2024-10-25 16:40:47 +02:00
models	Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels (#2688)	2024-10-25 16:40:47 +02:00
pb	chore: add pre-commit (#1569)	2024-02-16 11:58:58 +01:00
utils	Add support for FP8 KV cache scales (#2628)	2024-10-24 16:36:18 +02:00
__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	Support e4m3fn KV cache (#2655)	2024-10-17 10:42:16 +02:00
interceptor.py	feat: prefill chunking (#2600)	2024-10-16 12:49:33 +02:00
server.py	feat: prefill chunking (#2600)	2024-10-16 12:49:33 +02:00
tracing.py	Add OTLP Service Name Environment Variable (#2076)	2024-06-25 09:33:01 +02:00