biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] Make FP8 Linear Ops use kernel abstraction (#27814)

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm
2026-01-20 14:48:20 +08:00
committed by GitHub
parent e9c83cdc51
commit 148117ea2e
30 changed files with 1467 additions and 1038 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/quantization/test_compressed_tensors.py
View File

@@ -41,7 +41,7 @@ ROCM_AITER_SUPPORTED_INT8_MODEL = [
"nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2",
]
# TritonScaledMMLinearKernel only supports symmetric quantization.
# TritonInt8ScaledMMLinearKernel only supports symmetric quantization.
ROCM_TRITON_SCALED_MM_SUPPORTED_INT8_MODEL = [
"nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change",
"nm-testing/tinyllama-oneshot-w8-channel-a8-tensor",