mingg26andOpenAI Codex 259a209bfa [Kimi-K3][Perf] Prefetch ll_bf16 router weights for M=1 (#53524) ...

Signed-off-by: ming <ming@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>

2026-09-01 21:40:19 +00:00

..

cute_dsl

[Kimi-K3][Perf] Prefetch ll_bf16 router weights for M=1 (#53524)

2026-09-01 21:40:19 +00:00

mixed_precision

[ROCm][Bugfix] Fix Triton W4A16 bug in determining if transpose is required for GPTQ/AutoGPTQ (#48998)

2026-08-17 12:26:05 +00:00

mxfp4

[ROCm] remove VLLM_ROCM_USE_AITER_FP4_ASM_GEMM environment variable; make w4a4 use the preshuffle triton+asm by default (#53141)

2026-08-28 18:59:53 +00:00

mxfp6

[Docs] Fix two docs build warnings (#51014)

2026-08-04 05:29:04 -07:00

mxfp8

[ModelOpt] Redesign the LinearMethod classes using the generic QuantKey-driven method (#49381)

2026-09-01 16:28:56 -04:00

nvfp4

[Kernel] add Flashinfer cutedsl w4a16 linear (#53014)

2026-09-01 02:49:14 +00:00

scaled_mm

[Bugfix][Quantization] Support CT block FP8 with Marlin (#52966)

2026-08-19 12:41:26 -07:00

__init__.py

[Kernel] add Flashinfer cutedsl w4a16 linear (#53014)

2026-09-01 02:49:14 +00:00

base.py

[Refactor] Remove dead code for quantization (#52221)

2026-08-16 13:10:16 -04:00

zentorch_utils.py

[CPU][Zen] Route BF16 MoE inference through zentorch on AMD (#44201)

2026-08-10 23:20:05 -07:00