Wentao Ye b2f9e4caa4 [DSv4 Perf] Adaptive topk width, 1.0% E2E throughput improvement (#50004) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2026-07-27 15:56:52 -04:00

..

deepseek_v4

[DSv4 Perf] Adaptive topk width, 1.0% E2E throughput improvement (#50004)

2026-07-27 15:56:52 -04:00

deepseek_v32

[Perf] Fix moe reduce_scatter perf regression by removing additional comm, 5% E2E throughput gain back. (#48763)

2026-07-25 16:36:19 +00:00

inkling

[ROCm] [Model] Enable TML inkling (#48841)

2026-07-27 10:05:46 +00:00

minimax_m3

[Bugfix][MiniMax-M3] Fix token-major top-k buffer handling in Triton … (#49149)

2026-07-25 06:45:27 -07:00

__init__.py

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

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