Juntian Liu 609731e8f5 [Perf][DSv4.1] Restore the fused query RMSNorm + MXFP8 quantization path (#57679) ...

Signed-off-by: Juntian Liu <Juntianl777@gmail.com>

2026-09-25 01:39:03 +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

[Perf][DSv4.1] Restore the fused query RMSNorm + MXFP8 quantization path (#57679)

2026-09-25 01:39:03 +00:00

dots3_note

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

glm5next

[Bugfix] GLM-5.3-Flash: launch the kpool paged MQA logits in the varlen mode its schedule was built with (#55270)

2026-09-25 00:13:55 +00:00

hy_v4

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

inkling

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

kimi_k3

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

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

minimax_m3

[Minimax-M3][Perf] Use triton_mrope for vision tower + int64 offset fix for triton_mrope (#58526)

2026-09-24 18:30:32 -07:00

qwen4_exp

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

__init__.py

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

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