What's Changed

• rm unused lmdeploy patch by @jinminxi104 in #310
• fix prefix caching by @yao-fengchen in #307
• fix PA param list by @jinminxi104 in #314
• [Ascend] support qwen3next by @wanfengcxz in #304
• remove unused import by @jinminxi104 in #317
• fix ci by @jinminxi104 in #318
• add mix_prefill test case by @yao-fengchen in #320
• fix re-capture in RL by @jinminxi104 in #319
• optimize rope and remove unused l2norm_fwd by @wanfengcxz in #316
• fix state dtype and refactor gdn kernel by @wanfengcxz in #321
• Bump028 by @jinminxi104 in #323

Full Changelog: v0.2.7...v0.2.8

Contributors

• @jinminxi104
• @wanfengcxz
• @yao-fengchen

What's Changed

• support ep by @yao-fengchen in #237
• adapt for s1-pro dp*tp_ep by @yao-fengchen in #305
• Copilot/add all routed experts support by @jinminxi104 in #293
• fix padding by @jinminxi104 in #306
• Bump version to 0.2.7 by @jinminxi104 in #309

Full Changelog: v0.2.6...v0.2.7

Contributors

• @jinminxi104
• @yao-fengchen

What's Changed

• [ascend] fix paged_prefill and use max_batchsize as max capture size by @tangzhiyi11 in #294
• [ascend] update multinode doc by @tangzhiyi11 in #296
• Fix refact by @jinminxi104 in #297
• Patch rotary_embedding builder and DlinferSoftmaxTopKImpl by @tangzhiyi11 in #301
• patch profile npu by @jinminxi104 in #300
• [fix]fix camb run qwen vl by @huaxiaofen in #298
• fix neg seqlen by @jinminxi104 in #302
• bump to 0.2.6 by @jinminxi104 in #303

New Contributors

• @huaxiaofen made their first contribution in #298

Full Changelog: v0.2.5...v0.2.6

Contributors

• @tangzhiyi11
• @jinminxi104
• @huaxiaofen

What's Changed

• [Maca] Fix qwenvl and internvl using mcoplib by @wanfengcxz in #279
• refactor code by @yao-fengchen in #282
• [ascend] patch dptp moe by @tangzhiyi11 in #285
• fix qwen vl mask temporarily by @yao-fengchen in #286
• [ascend] support w8a8 using torch_npu ops by @wanfengcxz in #284
• [ascend] disable compile dicp and use torch_npu replay by @tangzhiyi11 in #287
• fix qwen vl vision part flash-attention by @yao-fengchen in #288
• [ascend] add multinodes doc by @tangzhiyi11 in #290
• Copilot/add patch for ascend in lmdeploy by @jinminxi104 in #291
• Copilot/update capture batch size logic by @jinminxi104 in #292
• Copilot/bump version to 025 by @jinminxi104 in #289

New Contributors

• @wanfengcxz made their first contribution in #279

Full Changelog: v0.2.4...v0.2.5

Contributors

• @tangzhiyi11
• @jinminxi104
• @wanfengcxz
• @yao-fengchen

• 支持华为A3
• 支持华为aclgraph

• 华为
  • 支持A3上的Qwen系列
  • 修复图模式下的内存泄漏问题
• 沐曦
  • Refine代码。适配最新软件栈。

华为

• 多卡下默认使用ray,修复稳定性问题
• 其他bug fix

华为

• MoE优化

What's Changed

• revert ci by @jinminxi104 in #198
• [ascend]remove attention patch in lmdeploy by @yao-fengchen in #194
• [feat]support ascend w8a8 graph_mode by @yao-fengchen in #191
• Refactor rope by @yao-fengchen in #199
• change ci setting by @jinminxi104 in #202
• fix ascend awq by @yao-fengchen in #204
• [ascend]Optimize moe by @yao-fengchen in #203
• Bump018 by @jinminxi104 in #209

Full Changelog: v0.1.7...v0.1.8

Contributors

• @jinminxi104
• @yao-fengchen

华为&沐曦

• 支持多节点
• 支持mla,支持dsv2

What's Changed

• [maca] support deepseekv2 for maca backend. by @Reinerzhou in #133
• [camb]fix fused_moe param order by @JackWeiw in #173
• [camb]add w8a8 support by @JackWeiw in #176
• [ascend] add new_empty op and opt reshape ops by @tangzhiyi11 in #178
• fix glm-4v by @jinminxi104 in #184
• revert ci by @jinminxi104 in #187
• default enable npu launch by @jinminxi104 in #188
• [ascend] support multi ndoes by @tangzhiyi11 in #190
• [maca] support multinode for maca. by @Reinerzhou in #192
• [ascend] remove allreduce group in eager mode by @tangzhiyi11 in #193
• [ascend]support mla by @yao-fengchen in #182
• bump version to 0.1.7 by @jinminxi104 in #195

Full Changelog: v0.1.6...v0.1.7

Contributors

• @tangzhiyi11
• @jinminxi104
• @yao-fengchen
• @Reinerzhou
• @JackWeiw