[Feature] DeepSeek V3/R1 INT8 Quantization (channel-wise) (#3888)

Co-authored-by: yych0745 <1398089567@qq.com> Co-authored-by: sleepcoo <sleepcoo@gmail.com> Co-authored-by: b0urnee <2769086541@qq.com>
2025-03-07 12:54:52 +08:00
parent 63ee26d162
commit c7f254468f
5 changed files with 369 additions and 21 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -61,6 +61,7 @@ suites = {
        "test_w8a8_quantization.py",
        "test_fp8_kernel.py",
        "test_block_int8.py",
+        "test_int8_kernel.py",
        "test_reasoning_content.py",
    ],
    "nightly": [