"tests/kernels/quantization/untest_marlin_gemm.py" did not exist on "0f41fbe5a370c0b87bb9a038be592c9272d46364"
- 30 Aug, 2024 2 commits
-
-
afeldman-nm authored
-
Cyrus Leung authored
-
- 29 Aug, 2024 12 commits
-
-
chenqianfzh authored
-
Harsha vardhan manoj Bikki authored
Co-authored-by:Harsha Bikki <harbikh@amazon.com>
-
Dipika Sikka authored
-
Isotr0py authored
-
kushanam authored
Co-authored-by:youkaichao <youkaichao@126.com>
-
Pavani Majety authored
[Core][Kernels] Enable FP8 KV Cache with Flashinfer backend. + BugFix for kv_cache_dtype=auto (#7985) Co-authored-by:
Simon Mo <simon.mo@hey.com> Co-authored-by:
Cody Yu <hao.yu.cody@gmail.com>
-
Alexander Matveev authored
-
Jonas M. Kübler authored
-
youkaichao authored
-
Peter Salas authored
-
youkaichao authored
-
Nick Hill authored
Co-authored-by:Robert Shaw <rshaw@neuralmagic>
-
- 28 Aug, 2024 13 commits
-
-
youkaichao authored
Co-authored-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
bnellnm authored
-
Mor Zusman authored
-
rasmith authored
[Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and awq_gemm to support AWQ (#7386)
-
Pavani Majety authored
Co-authored-by: -
Cyrus Leung authored
-
youkaichao authored
-
Cody Yu authored
-
Alexander Matveev authored
-
Cyrus Leung authored
-
bnellnm authored
[Bugfix] Allow ScalarType to be compiled with pytorch 2.3 and add checks for registering FakeScalarType and dynamo support. (#7886)
-
youkaichao authored
-
Peter Salas authored
-
- 27 Aug, 2024 11 commits
-
-
Jonathan Berkhahn authored
-
zifeitong authored
-
Dipika Sikka authored
Co-authored-by:ElizaWszola <eliza@neuralmagic.com>
-
youkaichao authored
-
Isotr0py authored
-
Kunshang Ji authored
-
Patrick von Platen authored
-
Cody Yu authored
-
youkaichao authored
-
Megha Agarwal authored
Co-authored-by:Alexander Matveev <alexm@neuralmagic.com>
-
Dipika Sikka authored
-
- 26 Aug, 2024 2 commits
-
-
omrishiv authored
Signed-off-by:omrishiv <327609+omrishiv@users.noreply.github.com>
-
youkaichao authored
-
