iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
23,341 Commits 3 Branches 0 Tags
patches
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Wentao Ye 8e25bbca19 [Refactor] Remove dead code multiple places (#61843) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-16 15:01:07 +00:00
Wentao Ye 54d9b1cb48 [GLM5.3 Perf] Inplace update draft decode metadata, 1.7% E2E Throughput Improvement (#61873) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-15 20:20:12 +00:00
Wentao Ye c19c263ac8 [GLM 5.3 Perf] Handle two elements at the same time for per token group quant, 2.8% E2E ITL improvement (#60927) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-13 13:06:41 -07:00
Wentao Ye 2f18d13cf0 [GLM5.3 Perf] Enable fp8 kv cache for GLM5.3 Flash by default, 9.8% E2E Throughput Improvement (#61228) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-13 15:29:17 -04:00
Wentao Ye d0948f754d [Bug] Honor spec decode draft model config (#61240) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-12 15:13:23 -04:00
Wentao Ye 276fbcff27 [Deprecation] Remove scheduled deprecated items (#60923) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-10 15:45:33 -04:00
Wentao Ye 3709632ff2 [Refactor] Remove dead code multiple places (#60120) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-10 15:41:10 +00:00
Wentao Ye 838526c7e5 [Compile] Fix sampler compile warning (#60680) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-10 08:09:45 -07:00
Wentao Ye fba31f31a9 [GLM5.3 Perf] Switch to fp8 kv cache by default for GLM, 2.3%~5.5% E2E Throughput Improvement (#60140) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-06 12:54:20 -04:00
Wentao Ye 3e182185aa [Deprecation] Deprecate sonet dataset as scheduled (#60129) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-06 08:15:12 -04:00
Wentao Ye 74c5cbcd7b [Bugfix][MRV2][Spec Decode] Honor dynamic K in autoregressive speculators, 1.2~1.3x kernel perf improvement (#57053) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-05 14:54:11 -04:00
Wentao Ye 8bdd8d847d [GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1 (#57443) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-02 20:05:27 -04:00
Wentao Ye f700178f90 [Refactor] Remove dead env and config (#59781) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-02 18:07:20 +00:00
Wentao Ye 4e4d75c459 [GLM5.3 Perf] Reuse sparse MLA index conversion across layers, 3.5~3.9x kernel performance improvement (#59464) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-02 17:37:45 +00:00
Wentao Ye 4d6874d137 [GLM 5.3 Perf] Skip qlnorm calculation for MHA, 4.4~7.7% E2E TTFT Improvement (#58845) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-10-01 15:13:57 +08:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 834ad456d3 [Refactor] Remove dead tests code (#58916) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-09-30 04:39:03 +00:00
Wentao Ye 3576691c42 [GLM5.3 Bug] Fix sparse indexer attn topk backend selection (#58594) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-26 11:35:28 -04:00
Wentao Ye bf93e1f92c [Refactor] Remove dead tests utils (#58803) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-26 09:16:53 -04:00
Wentao Ye c88f4824ff [GLM5.3 Perf] Optimize glm 5.3 metadata op, 1.6~4.8x kernel level performance improvement (#58450) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-25 13:15:18 -04:00
Wentao Ye 3c42385d7d [Refactor] Remove dead or duplicate tests (#58446) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-24 10:29:56 -04:00
Wentao Ye 355d789f0d [Compilation] Fix QuTLASS compilation with PyTorch 2.13 (#58173) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-22 20:43:28 -07:00
Wentao Ye fae5cbfc8b [Refactor] Remove dead code multiple places (#58002) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-22 16:36:03 -04:00
Wentao Ye 4868312128 [Refactor] Remove dead kernel code (#57621) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-20 10:39:23 -07:00
Wentao Ye 36fa72d2d0 [GLM5.3 Perf] Size the GLM-5 sparse indexer decode workspace, 3072 MiB GPU memory saved (#57701) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-19 16:57:01 -04:00
Wentao YeandFlora Feng f3aa88d230 [Kimi K3 Bug] Fix kimi k3 reasoning parser (#57098) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
 2026-09-17 10:05:52 -07:00
Wentao Ye 91a4c40b45 [Compile] Fix compile warning #177-D (#56609) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-17 05:04:56 -07:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 18f8aa0465 [Refactor] Remove dead kernel code (#56845) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-09-15 13:17:53 -07:00
Wentao Ye 9f03b510c3 [DSv4 Bug] fix dsv4 start up error NotImplementedError: DeepSeek V4 MegaMoE currently requires expert parallel (#55914) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-13 20:22:08 -04:00
Wentao Ye 5fe77aecfc [Deprecation] Deprecate items scheduled for 0.29 (#55353) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-11 08:17:02 -07:00
Wentao Ye 1e1060f998 [Kimi Perf] Group fp8 mla cahche insertion, 4~6x kernel level performance improvement for small batch (#55356) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-11 08:16:57 -07:00
Wentao Ye 86aca66191 [Kimi K3 Perf] Avoid KDA mixed-batch gather/scatter, 5.2%~7.7% E2E Throughput Improvement (#56159) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-10 17:57:01 +08:00
Wentao Ye bfb443a6b6 [Kimi Bug] Fix kda ima Triton Error [CUDA]: an illegal memory access was encountered (#55924) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-08 14:07:54 -07:00
Wentao Ye 6b15bea080 [Refactor] Remove utils dead code (#53941) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-08 11:22:09 -04:00
Wentao Ye 07950d4734 [Kimi Bug] Fix kimi k3 startup cuda graph issue with recoverSSM (#55774) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-08 10:29:53 -04:00
Wentao Ye 869f78732b [Kimi Bug] Fix kimi k3 AssertionError assert 0 <= checkpoint_idx < len(blocks) (#55747) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-07 22:34:48 -04:00
Wentao Ye a56654d6de [K3 Perf] Enable DSV3 GEMM for inner-contiguous and row-strided tensors, 12%~81% kernel performance improvement (#54565) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-02 12:22:40 -07:00
Wentao Ye fc72fc39ac [Kimi Bug] Fix cannot access local variable 'active_non_spec_mask_cpu' (#54781) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-01 21:08:50 +00:00
Wentao Ye 6c58595c2d [Feature] Avoid flashinfer autotune each time when vllm source change (#54794) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-09-01 15:03:30 -04:00
Wentao Ye 91752b7a3e [K3 Bug] Fix Kimi-K3 RecoverSSM startup failure 'MambaAttentionBackendEnum.GDN_ATTN declares 4 states, but provides 2 state copy funcs' (#54634) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-31 23:22:49 +00:00
Wentao Ye 3a2ed6cbae [Kimi Bug] Fix gdn build_attn_metadata 'KimiK3KDAMetadataBuilder' object has no attribute 'layer_names' (#54636) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-31 19:21:01 -04:00
Wentao Ye 9818bb3db8 [Kimi Perf] Tune hopper low latency gemm kernel, 4%~97% performance improvement (#54088) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-27 16:48:53 -04:00
Wentao Ye 76cfe1cd88 [Kimi K3 Perf] Optimize eh_proj linear calculation, 12.9 ~ 25.2% kernel performance improvement (#53942) 2026-08-26 17:08:02 -04:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> a5e0045433 [Refactor] Remove dead code quantization 2 (#52821) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-08-25 20:28:44 -07:00
Wentao Ye a447955aca [Kimi Bug] Fix k3 torch.AcceleratorError: CUDA error: an illegal memory access was encountered (#53773) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-25 17:38:48 -07:00
Wentao Ye 0e30bd62fe [CI Bug] Fix kimi test AssertionError: Aligned Mamba state indices must be precomputed (#53766) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-25 15:06:14 -04:00
Wentao Ye 384d079697 [Perf] Autotune batch invariance triton kernel in blackwell, 33.6% E2E latency reduction (#53649) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-25 15:06:01 -04:00
Wentao Ye 70021a0081 [Mypy Fix] Mypy fix for "vllm/model_executor/models/[gG]" (#53616) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-25 09:47:16 -07:00
Wentao Ye 41729fc53b [K3 Perf] Optimize k3 mamba metadata preparation, 6.6~7.6x kernel performance improvement (#52388) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-25 11:00:28 -04:00
Wentao Ye f59bb0bd8c [Refactor] Refactor batch invariance folder (#53619) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-24 14:31:36 -07:00
Wentao Ye 29c9af5211 [Kimi K3 Refactor] Add UnfinalizedMoEOutput proto following up for #53152 (#53310) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-24 11:21:11 -04:00
Wentao Ye 811d12ee26 [Mypy Fix] Mypy fix for "vllm/model_executor/models/[eE][fF]" (#53381) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-22 15:41:27 -04:00
Wentao YeZiming HuangOpenAI Codex
 		9eb9d9d395 [Perf] Support internal prefill checkpoints for Mamba prefix caching, 9%~25% TTFT improvement (#52789) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Ziming Huang <zelda.huanghuang@gmail.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Ziming Huang <zelda.huanghuang@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-08-22 10:32:40 -07:00
Wentao Ye e6f35d3c69 [DSv4 Perf] Adaptive topk width for dsv4, making #50004 back (#52823) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-21 12:11:45 -07:00
Wentao YeYongye ZhuOpenAI Codex
 		7a2fdbaac4 [K3 Perf] Fuse MXFP4 top-k finalization into latent-tail, ~5% E2E latency reduction (#53152) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
 2026-08-21 13:29:59 -04:00
Wentao Ye 7d7b6f26f4 [Refactor] Remove dead code for quantization (#52221) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-16 13:10:16 -04:00
Wentao Ye 9a276d6375 [Mypy Fix] Mypy fix for "vllm/model_executor/models/[cC][dD]" (#52003) 2026-08-13 11:33:55 +08:00
Wentao Ye 23f360edaa [CI Bug] Fix ci moe test (#52009) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-12 21:28:53 +00:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> fe889ac925 [K3 Perf] Flash kda out kernel for prefill, 1.1~1.4x kernel performance improvement (#51311) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-08-12 14:51:48 -04:00
Wentao Ye 0fb168e6ee [CI Bug] Fix ci qwen3.5 (#52007) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-12 13:22:09 -04:00
Wentao Ye fd04edef3e [Refactor] Delete dead code in models (#51838) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-11 15:44:26 -04:00
Wentao Ye 4988df2eb8 [Config] Update default _max_num_batched_tokens from 8192 to 16384 (#51726) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-11 11:09:34 -04:00
Wentao Ye 0914ed2e81 [Perf] Adaptive budget for spec scheduled input tokens, ~60% better Kimi K3 DSpark TTFT (#51725) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-10 20:52:21 -07:00
Wentao Ye c39076feff [CI Test] Add specific unit test for mrv2 offloading (#51440) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-07 22:49:45 +00:00
Wentao Ye 4a11ed5bc4 [DSv32/GLM Perf] Skip short prefill topk for dense mha layer, 97.9% kernel level latency reduction (#51298) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-07 20:30:42 +00:00
Wentao Ye a671679e9f [MRv2 Feature] MR v2 weight offloading support (#51413) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-07 13:20:21 -06:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 56a4b63d44 [K3 Perf] Optimize k3 dspark fused kv, 4.5~4.6x kernel performance improvement (#50585) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-08-07 12:16:11 -07:00
Wentao Ye c84789c40b [Refactor] Remove kernel dead code (#51051) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-07 01:20:19 -07:00
Wentao Ye adc3e03517 [Mypy Fix] Mypy fix for "vllm/model_executor/models/[aA][bB]" (#48977) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-06 19:30:15 +00:00
Wentao Ye ad5280255b [GLM Perf] DSv32/glm use skip topk for MTP case, 2.0x kernel performance improvement (#50904) 2026-08-06 01:48:36 -07:00
Wentao Ye 877975897d [K3 Perf] Combine multiple all gather together for SP, 1.5~3x kernel level performance improvement (#51070) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-05 17:42:41 -04:00
Wentao Ye e76b71f659 [CI Bug] Fix pydantic_core._pydantic_core.ValidationError: Input should be a valid integer (#51179) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-05 20:57:47 +00:00
Wentao Ye 613411a90c [CI Bug] Fix Chunked prefill is required for mamba cache mode 'align'. (#51177) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-05 11:33:45 -07:00
Wentao Ye 23c0f337b7 [CI bug] Fix Each KV cache group's real block_size must be divisible by has h_block_size (#51180) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-05 14:03:17 -04:00
Wentao Ye d31de3c421 [Kimi K3 Perf] option to shard the shared expert for non mega case, 16.98 GiB memory/GPU saved (#50912) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-04 14:00:44 -04:00
Wentao Ye 4f819f801b [Model Runner v2] E/P/D disaggregation support (#38390) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-08-04 15:52:23 +00:00
Wentao Ye 0cf49a5d15 [Refactor] Remove multiple dead codes (#50285) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-08-03 10:59:08 -04:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> df71917cf1 [DSv4 Perf] Optimize workspace reuse for eager break, 3.9% E2E TTFT improvement. (#49236) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-31 08:45:58 -07:00
Wentao Ye 0bff0ce5d3 [Kimi K3 Bug] Fix deepgemm support for kimi k3 (#50458) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-30 20:10:16 -04:00
Wentao Ye 837eae6458 [DSv4 Perf] Remove redundant full kernel for dsv4, 1.88x kernel performance improvement (#50298) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-30 11:39:07 -04:00
Wentao Ye 904fae8be1 [DSv4 Perf] Fix redundant memory allocation and copy for dsv4 pp buffer, 448 MiB GPU memory saved (#50312) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-30 11:38:51 -04:00
Wentao Ye 82642d7d6c [Perf] RMSNorm uncontiguous support, 1.2~3.1x kernel performance improvement (#49750) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-07-29 13:45:38 -07:00
Wentao Ye b5bcb3ce88 [Refactor] Remove dead code in multiple files (#49745) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-27 15:58:26 -04:00
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
Wentao Ye 7fe6d3c76b [Perf] Fix moe reduce_scatter perf regression by removing additional comm, 5% E2E throughput gain back. (#48763) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-25 16:36:19 +00:00
Wentao Ye b354734d17 [Bug] Fix batch invariance rms norm comparison (#49603) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-23 12:27:38 -06:00
Wentao Ye b0cb1da1bd [DSv4 Perf] Skip topk and router when not needed, 3.4% E2E TTFT improvement for Decode case (#49486) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-23 13:08:08 -04:00
Wentao Ye 37e370fe93 [DSv4 Perf] Skip empty c128 kernel launch, around 2x kernel performance improvement. (#48957) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-22 10:55:20 -04:00
Wentao Ye b5433b6f50 [Perf] Optimize dsv4 routing using specialized kernel, 2.94% E2E TPOT improvement (#48660) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-17 13:35:06 -07:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 877dae9c68 [Refactor] Remove deepseek dead code (#48780) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-17 14:57:13 +00:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> f17be06fbe [Perf] Optimize clamp to clamp_ (#48143) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-16 18:41:07 -04:00
Wentao Ye 626c90b2d5 [Refactor] Move fla to third party (#48500) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-16 19:22:36 +01:00
Wentao Ye 2dab187f75 [Perf] Optimize fused_topk_bias for DSv4, 1.5~2x kernel performance improvement (#47463) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-15 23:40:55 +00:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 4238b011a7 [Feature] Migrate moe sp support to non-torch compiled path for GLM5.2 (#47881) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-15 23:33:15 +00:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 442c421e79 [Perf] Remove redundant repeat and copy for dsv4, 1.8% E2E TPOT improvement. (#48137) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-15 00:48:10 +00:00
Wentao Ye 1ff9429655 [CI Bug] Fully solve accuracy issue for DSv3.2 + MTP + Sequence Parallel (#48036) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-14 10:00:24 -04:00
Wentao Ye b3cfca996c [Mypy Fix] Split mypy work (#48490) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-13 12:42:42 +00:00
Wentao Ye e257faf87d [Refactor] Remove unused rocm kernel combine_topk_swa_indices_ragged (#48158) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-10 09:33:07 -04:00
Wentao Ye 3f99883d97 [CI Bug Fix] Temp fix for v3.2 accuracy (#47902) 2026-07-07 16:36:03 -04:00
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> bdc6f3bfa1 [Bug] Fix tmp directory for lm_eval (#47755) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-07 16:40:12 +00:00
Wentao Ye f70caef48b [Perf] Cache token_to_req_indices for dsv4, 5x~6x kernel performance improvement (#47474) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-07-06 11:17:46 -04:00