Fangzhou AiandClaude Opus 5.5 721d0e5c11 [ROCm][DSv4.1][Perf] Emit MXFP8 from the sparse decode reduce and run wo_a as a grouped FP8 GEMM (#58456) ...

Signed-off-by: fai <fangzhouai@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

2026-09-24 11:58:14 +00:00

..

common

[5/N][warmup][DSv4] Migrate NVIDIA CuTeDSL attention kernels (#53566)

2026-09-12 00:05:59 -04:00

deepseek_v4

[Dependency] Upgrade FlashInfer version to 0.7.0 (#58069)

2026-09-23 22:45:23 -07:00

deepseek_v32

[ROCm][Model][Bugfix] Enable GLM-5.2-MXFP4 on the deepseek_v32 path and fix sparse attention correctness (#51915)

2026-09-22 18:08:51 -05:00

deepseek_v41

[ROCm][DSv4.1][Perf] Emit MXFP8 from the sparse decode reduce and run wo_a as a grouped FP8 GEMM (#58456)

2026-09-24 11:58:14 +00:00

dots3_note

[Spec decode] Support variable-length decode for Kimi-K3 adaptive ver (#52988)

2026-09-22 20:43:32 -07:00

glm5next

[Bugfix][Model][Spec Decode] Defer disposable GLM MTP head (#55442)

2026-09-22 20:08:27 +00:00

hy_v4

[Perf][ROCm] Add a ROCm path for Hy4 and compile the backbone (#57526)

2026-09-21 08:20:43 +00:00

inkling

[Multimodal] Type dummy options per modality (#57576)

2026-09-18 17:29:11 +01:00

kimi_k3

[Refactor][Quantization] Make FP8 and MLA weight transforms reusable pure functions (#57732)

2026-09-23 01:16:20 -07:00

minimax_m3

[Perf] Use Conv3dLayer for MiniMax M3 patch embedding (#58512)

2026-09-24 00:41:36 -07:00

qwen4_exp

[Kernel] Resubmit PR 48666 - Gemma4 FP8 KV FA4 head dim 512 backend selection (#53175)

2026-09-23 20:29:06 -07:00

__init__.py

[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)

2026-05-18 19:50:02 -07:00