Logo
Explore Help
Register Sign In
minke.yu/sglang
Watch 1
Star 0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
Files
3f36fc08331f64cd63c4fbbdf39cc402f38bb38b
sglang/test/registered/kernels/benchmark/quantization
T
History
Jayden YuJayden YuXiaoyu Zhang
bb9e9d5632 [Perf] mlp: Fuse dense SwiGLU with block-FP8 quantization on decode (#45219)
Co-authored-by: Jayden Yu <jaydenyu@fb.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
2026-10-23 07:49:39 +08:00
..
bench_awq_dequantize.py
Delete cutlass_mla, non-Marlin GPTQ, AWQ AOT kernel, and Dual Chunk Flash Attention (#32114)
2026-09-10 15:12:01 +08:00
bench_hadamard.py
[Kernel] Add inventory guards and clean benchmark layout (#32788)
2026-07-30 09:03:24 +08:00
bench_per_tensor_quant_fp8.py
[Kernel] Classification cleanup: unify _jit_ naming, drop empty/model groups, add elementwise (RFC #29630) (#32148)
2026-07-23 13:47:02 +08:00
bench_per_token_group_quant_8bit_v2.py
[Kernel] Classification cleanup: unify _jit_ naming, drop empty/model groups, add elementwise (RFC #29630) (#32148)
2026-07-23 13:47:02 +08:00
bench_per_token_group_quant_masked.py
[Refactor] kernels/diffusion/tests: Prune dead code and fix tests that never ran (#44690)
2026-10-19 08:55:47 +08:00
bench_per_token_group_quant.py
[Perf] mlp: Fuse dense SwiGLU with block-FP8 quantization on decode (#45219)
2026-10-23 07:49:39 +08:00
bench_per_token_quant_fp8.py
[JIT Kernel] Migrate per-token FP8 quantization from AOT to JIT (#34257)
2026-08-11 20:40:40 +08:00
Powered by Gitea Version: 1.27.3 Page: 851ms Template: 3ms
GitHub Default Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API