wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-08-15 12:54:49 +08:00
Code Issues Packages Projects Releases Wiki Activity
2,401 Commits 1 Branch 0 Tags
baaedfdb2d3f1d70b7dbcde08b083abfe6017a92
Commit Graph
10 Commits
Author SHA1 Message Date
jon-chuang 50b8d08dbd [Misc/Testing] Use torch.testing.assert_close (#7324) 2024-08-16 04:24:04 +00:00
Lucas Wilkinson a8d604ca2a [Misc] Disambiguate quantized types via a new ScalarType (#6396) 2024-08-02 13:51:58 -07:00
HandH1998 6512937de1 Support W4A8 quantization for vllm (#5218) 2024-07-31 07:55:21 -06:00
Alexander Matveev 75acdaa4b6 [Kernel] Increase precision of GPTQ/AWQ Marlin kernel (#6795) 2024-07-27 17:52:33 -04:00
Alexander Matveev 396d92d5e0 [Kernel][Core] Add AWQ support to the Marlin kernel (#6612) 2024-07-21 19:41:42 -04:00
Robert ShawandRobert Shaw b675069d74 [ Misc ] Refactor Marlin Python Utilities (#6082) 
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
 2024-07-11 15:40:11 +00:00
Michael Goin 47f0954af0 [Kernel] Expand FP8 support to Ampere GPUs using FP8 Marlin (#5975) 2024-07-03 17:38:00 +00:00
Alexander Matveev 6066253296 Marlin 24 prefill performance improvement (about 25% better on average) (#4983) 2024-05-23 02:39:27 -04:00
Alexander Matveev 27ce85476e [Kernel] Add marlin_24 unit tests (#4901) 2024-05-19 11:37:34 -04:00
alexm-nm 5c342570d7 Add marlin unit tests and marlin benchmark script (#4815) 2024-05-16 09:36:49 -04:00