|
124fac10cb
|
[Bugfix] Fix RMSNorm kernels to multiply in weight's native dtype (#42379)
Signed-off-by: Lanze Liu <lanzetech@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-29 23:16:53 -07:00 |
|
|
|
e9499996df
|
[BugFix][Platform] Fix import vllm.platforms.rocm error on non-CUDA test_gpt_oss.py (#43571)
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-29 23:16:49 -07:00 |
|
|
|
c0056b19bf
|
[ROCm] cmake: support PYTORCH_FOUND_HIP for torch 2.13 native HIP language support (#43881)
Signed-off-by: nemanjaudovic <nudovic@amd.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-05-29 22:16:57 -07:00 |
|
|
Andreas KaratzasandGitHub
|
ef8840adc7
|
[ROCm][CI] Fix failure in the Phi3V pooling test (#44028)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-05-30 12:14:37 +08:00 |
|
|
Flora FengandGitHub
|
1a096d8208
|
[Refactor] Remove dead current_tool_name_sent assignments from tool parsers (#43997)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-29 21:45:15 -04:00 |
|
|
Gagan DhakreyandGitHub
|
1e2ce5d11a
|
offload prompt_embeds decode in render_prompts_async to avoid blocking (#43792)
Signed-off-by: Gagan Dhakrey <gagandhakrey@gmail.com>
|
2026-05-30 01:36:34 +00:00 |
|
|
|
559d6710bf
|
[PERF]MiniMax-M2 gate kernel (#38445)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: qianlihuang <91178480+qianlihuang@users.noreply.github.com>
Co-authored-by: Yiliu Dong <91178480+qianlihuang@users.noreply.github.com>
|
2026-05-29 18:28:34 -07:00 |
|
|
bnellnmandGitHub
|
187457a952
|
Revert "[MoE Refactor] Migrate MoeWNA16Method quantization to MK orac… (#44033)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-05-29 16:45:29 -07:00 |
|
|
|
8fad266507
|
[CI] Fix smoke test step key to bypass block gate (#43974)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-05-29 16:28:32 -07:00 |
|
|
Flora FengandGitHub
|
8c6daf6e2f
|
[CI] Remove duplicate Harmony test coverage (#44023)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-29 22:52:46 +00:00 |
|
|
bnellnmandGitHub
|
7b98f498cd
|
[MoE Refactor] Remove supports_expert_map (#43108)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-05-29 17:26:56 -04:00 |
|
|
|
106aa92f04
|
[MoE Refactor] Migrate MoeWNA16Method quantization to MK oracle (#42647)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-05-29 17:19:31 -04:00 |
|
|
yzong-rhandGitHub
|
46409fd2a1
|
[Fronten] Clean up stop_token_ids override for Harmony (#44009)
Signed-off-by: Yifan Zong <yzong@redhat.com>
|
2026-05-29 13:28:06 -07:00 |
|
|
|
38b864d81d
|
[Metrics] Exclude KV transfer tokens from iteration_tokens_total (#43346)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-05-29 19:56:44 +00:00 |
|
|
Wentao YeandGitHub
|
5dbf1605a0
|
[Feature] SSL support for dp supervisor (#43688)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-29 19:28:12 +00:00 |
|
|
Kevin H. LuuandGitHub
|
acbc203340
|
Add @khluu to CODEOWNERS (#44019)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
|
2026-05-29 12:24:29 -07:00 |
|
|
Flora FengandGitHub
|
6de08e8b46
|
[CI] Remove redundant test_chat_with_tool_reasoning.py (#44011)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-29 19:23:56 +00:00 |
|
|
|
6aabe221a5
|
[CI] Make Model Executor test hangs fail fast with a traceback (#43971)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
v0.22.1rc0
|
2026-05-29 11:58:25 -07:00 |
|
|
Wentao YeandGitHub
|
739096a028
|
[Bug] Fix torch device issue for MOE permute (#44005)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-29 18:55:00 +00:00 |
|
|
czhu-cohereandGitHub
|
8b9deeec4b
|
[Bugfix] Fix Ray placement group allocation with grouped nodes (#43998)
Signed-off-by: <conway.zhu@cohere.com>
Signed-off-by: root <conway.zhu@cohere.com>
|
2026-05-29 12:51:05 -06:00 |
|
|
|
d07ad0693b
|
[Bugfix] Use storage_block_size in KV cache reshape for compressed specs (DeepSeek V4) (#43988)
Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-05-29 11:14:25 -07:00 |
|
|
|
4aaba00f92
|
[EPLB] Make async EPLB default (#43219)
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2026-05-29 18:07:16 +00:00 |
|
|
|
84b2a8a7e7
|
[MoE Refactor] WNA16 MoE backend selection into oracle module (#42553)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-05-29 13:11:17 -04:00 |
|
|
|
4ff865c38e
|
[Bugfix] Disable allreduce_rms_fusion when pipeline_parallel_size > 1 (#43616)
Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-05-29 22:57:43 +08:00 |
|
|
|
5502c3b52d
|
[Misc] added unit tests for the core pooling methods (#43818)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-05-29 14:40:31 +00:00 |
|
|
Chunyang WenandGitHub
|
f191d5630e
|
docs: clarify ITL acronym in optimization docs (#43922)
Signed-off-by: chunyang.wen <chunyang.wen@gmail.com>
|
2026-05-29 07:40:05 -07:00 |
|
|
|
11dfa3169d
|
Add vLLM library info to Hugging Face Hub requests (#43857)
Signed-off-by: Wauplin <lucainp@gmail.com>
Signed-off-by: Lucain Pouget <lucain@huggingface.co>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-05-29 14:04:58 +00:00 |
|
|
Li, JiangandGitHub
|
3f6f508e14
|
[Bugfix][CPU] Remove invalid extra deps (#43977)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-05-29 22:02:09 +08:00 |
|
|
Harry MellorandGitHub
|
0585b5ba2e
|
Skip docs build if PR doesn't affect docs (#43972)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-05-29 12:09:52 +00:00 |
|
|
Thien TranandGitHub
|
d2889722ff
|
[Bugfix] Corrupted MLA + linear attention (#43961)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-05-29 05:00:51 -07:00 |
|
|
|
0b56815a24
|
[ROCm][Perf] DSv3.2 MI355X TP4 decode-step orchestration cleanup (3 micro-opts) (#42982)
Signed-off-by: Frida Andersson <fanderss@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-29 04:26:57 -07:00 |
|
|
|
ab12aab127
|
[Bugfix] [ROCm] [DSV4] Fix AITER MXFP4 MoE weight loading and shuffle… (#42595)
Co-authored-by: MHYangAMD <MHYangAMD@users.noreply.github.com>
|
2026-05-29 04:08:33 -07:00 |
|
|
JartXandGitHub
|
0cff0741ff
|
[Kernel][ROCm] Native W4A16 kernel for AMD RDNA3 (gfx1100) — fp16 + bf16 (#41394)
Signed-off-by: JartX <sagformas@epdcenter.es>
|
2026-05-29 11:04:40 +00:00 |
|
|
|
60a7a2214f
|
[Bugfix] Fix Step3 pipeline parallel KeyError for residual tensor (#37622)
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-05-29 03:04:02 -07:00 |
|
|
Nicolò LucchesiandGitHub
|
7ebc0ec104
|
[CI] Nixl+SimpleCPUOffloadingConnector unit tests (#43871)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2026-05-29 02:40:42 -07:00 |
|
|
|
e8b5199973
|
[XPU] support MTP of gdn attention (#43565)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-29 17:10:24 +08:00 |
|
|
Simon DanielssonandGitHub
|
b7fb747d8d
|
[CI][ROCm] Don't skip MoRI-IO Connector tests (#43703)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
|
2026-05-29 17:06:23 +08:00 |
|
|
Kunshang JiandGitHub
|
30c6289b8e
|
[XPU] fix xpu install document triton-xpu version (#43947)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-29 02:05:12 -07:00 |
|
|
Andreas KaratzasandGitHub
|
ff990d0d32
|
[ROCm][CI] Fix AITER unified attention for encoder-decoder cross-attention (#43945)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-05-29 16:43:39 +08:00 |
|
|
ChaunceyandGitHub
|
87f12e5c7c
|
[Frontend]Responses API supports chat_template_kwargs (#43761)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-05-29 07:58:19 +00:00 |
|
|
kliuaeandGitHub
|
ab7521d77c
|
[ROCm][DSv4] Remove device pipeline stall in sparse attention (#43898)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-05-29 15:42:40 +08:00 |
|
|
|
94d3f4d205
|
[CPU Backend] CPU top-k and top-p sampling kernels using Triton (#43633)
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-29 15:02:39 +08:00 |
|
|
|
04516eabc8
|
[XPU] add gelu_tanh to xpu moe backend supported activations (#42822)
Signed-off-by: yintong-lu <yintong.lu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-29 14:37:20 +08:00 |
|
|
|
648c3ebee6
|
[CI] Separate non-root smoke tests from image build step (#43712)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-05-28 23:34:16 -07:00 |
|
|
|
22a58640b4
|
[9/n] Migrate attention and cache kernels to torch stable ABI (continued) (#43717)
Signed-off-by: Chris Leonard <chleonar@redhat.com>
Signed-off-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
Co-authored-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
|
2026-05-29 04:44:45 +00:00 |
|
|
|
710f077617
|
[Refactor] Remove dead code (#43234)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-29 00:29:56 -04:00 |
|
|
|
d63108fb18
|
[kv_offload] Skip decode-phase blocks in CPU offload (#43797)
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
|
2026-05-29 06:39:43 +03:00 |
|
|
|
9636709372
|
[XPU] add scale transpose to prepare_fp8_moe_layer_for_xpu and bump up kernels (#43277)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-29 03:22:51 +00:00 |
|
|
Weida HongandGitHub
|
dfe8ba7c80
|
Adjust design around encoder_cudagraph_forward (#42288)
Signed-off-by: Weida Hong <wdhongtw@google.com>
|
2026-05-29 03:02:52 +00:00 |
|
|
|
212deff2ec
|
[feat] add GlmgaProcessor specific logits in glm4_1v.py (#43575)
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-05-29 02:56:02 +00:00 |
|