 Ilya MarkovandRoberto L. Castro
|
f3bdb0e025
|
[Perf][MXFP4] Optimize activation quant for mxfp4. 3x kernel speedup, 5% throughput improvement (#63101)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
|
2026-10-26 16:51:55 -04:00 |
|
|
Chen Cheng
|
61b2527bdb
|
[Perf][MoE] Add H200 FP8 fused MoE config for Beam-1.0 TP8 (#62763)
Signed-off-by: Chen Cheng <85005591+ischencheng@users.noreply.github.com>
|
2026-10-26 15:39:00 +00:00 |
|
|
JartXandtjtanaa
|
00b6c4c565
|
[ROCm] Octave KV (ROCM_OCTAVE): native 3-bit KV cache backend for AMD GPUs (#59774)
Signed-off-by: JartX <sagformas@epdcenter.es>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-10-26 12:35:00 +08:00 |
|
|
+6
|
0f6b261910
|
[Model] Add Muse Spark Open support (#61879)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Jiahan Chang (Cyrus) <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: andyluo7 <43718156+andyluo7@users.noreply.github.com>
Co-authored-by: qizixi <22851944+zixi-qi@users.noreply.github.com>
Co-authored-by: haic0 <149741444+haic0@users.noreply.github.com>
Co-authored-by: Tianyu Guo <guoty@inferact.ai>
Co-authored-by: Shangdi Yu <yushangdi123@gmail.com>
Co-authored-by: JohnQinAMD <yanyuan.qin@amd.com>
Co-authored-by: Duncan Moss <6038874+djmmoss@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-26 09:56:09 +08:00 |
|
|
John CalderonandArtem Perevedentsev
|
fa2881ed19
|
[CI][Benchmarks] Fix attention smoke test backend names and failure exit status (#63177)
Signed-off-by: John Calderon <jcalderon@nvidia.com>
Co-authored-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-10-25 17:31:31 +02:00 |
|
|
Stephan ToivonenandClaude Opus 5.5
|
96bbaa300f
|
[ROCm][RDNA][Perf] W4A16: packed fp16 prefill dequant and tiles for gfx1151 (#60644)
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Signed-off-by: Stephan Toivonen <Stephan.Toivonen@amd.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-10-23 16:43:52 -06:00 |
|
|
|
b689feb9f2
|
[Benchmark] benchmark_moe: read Gemma 4's MoE shape from its text config (#62526)
Signed-off-by: Blaze-DSP <devsp0703@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-22 12:42:08 -04:00 |
|
|
Misha GoinandClaude Opus 5.5
|
b6078025b4
|
[Docs] Point users at --disable-flashinfer-autotune (#61489)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-21 10:55:26 -04:00 |
|
|
qli88
|
833349105b
|
[ROCm][Perf] HY4 preview perf boost (#58509)
Signed-off-by: Qiang Li <qiang.li2@amd.com>
|
2026-10-21 22:38:03 +08:00 |
|
|
|
900828023a
|
[CPU] Improve long-context MTP attention scheduling on AMX (#59082)
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
|
2026-10-21 12:18:30 +08:00 |
|
|
amd-xavierwang
|
4a30738d21
|
[ROCm][benchmark][perf] fix moe tuning script for RDNA (#41197)
Signed-off-by: xawang <xawang@amd.com>
|
2026-10-20 09:47:50 -05:00 |
|
|
|
9499c949be
|
[Quantizaiton][Feature] Pluggable KV Cache Data Types (#52670)
Signed-off-by: lcfenglinwan <lcfenglin@qq.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-10-20 10:03:14 +08:00 |
|
|
Dilber
|
dcf8158cdc
|
[Bugfix][Benchmark] Don't count content-free chunks as streamed outputs in chat (#62341)
Signed-off-by: Dilber P Shakir <dilbersha@gmail.com>
|
2026-10-19 02:54:00 +00:00 |
|
|
Jee Jee Li
|
e56b1603af
|
[Kernel]Add norm fused kernel for Step-5 Preview and Muse Spark Open (#62132)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-10-17 01:53:00 -07:00 |
|
|
Mikko TukiainenandCursor
|
47fd76e4ce
|
[ROCm][Perf] Route softmax MoE top-k, including fused shared-expert sigmoid, through AITER topk_gating (#56226)
Signed-off-by: Mikko Tukiainen <Mikko.Tukiainen@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-10-15 17:53:18 +00:00 |
|
|
Simon Danielsson
|
3f729dafcc
|
[Perf][ROCm][GLM-5.3-Flash] AITER prefill indexer topk (#60753)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
|
2026-10-14 13:48:56 -05:00 |
|
|
|
1484266938
|
[Perf] Improve _topk_topp_kernel() for masked logits (#61213)
Signed-off-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-10-12 16:01:11 -07:00 |
|
|
Misha GoinandClaude
|
e3a29aa9b3
|
[Bugfix][MoE] Size the permute scratch from its inputs (#60447)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-08 15:32:07 -04:00 |
|
|
|
458ba2edf8
|
[ROCm][Kimi-K3] Fuse AttnRes output with per-token FP8 input quantization (#59069)
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
|
2026-10-08 12:01:47 +00:00 |
|
|
Simon DanielssonandDouglas Lehr
|
87d9996abe
|
[ROCm][Perf][GLM-5.3-Flash] BF16 splitk kernel for sparse MLA decode (#58584)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
|
2026-10-07 21:37:51 -05:00 |
|
|
pmanczak
|
f7f62d1916
|
[XPU][MoE] Tune Triton fused MoE for Intel XPU (#53065)
|
2026-10-08 00:02:13 +08:00 |
|
|
Matthias Gehre
|
b267fe4881
|
[ROCm][Perf] W4A16: pad gfx11 weight and activation strides (#56301)
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
|
2026-10-06 08:22:33 -05:00 |
|
|
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 |
|
|
pmanczakandPawel Manczak
|
bdfb02674f
|
[XPU][Kernel] Tune Triton W8A8 block-FP8 GEMM for Intel B70 (#56063)
Signed-off-by: Pawel Manczak <203671809+pmanczak@users.noreply.github.com>
Co-authored-by: Pawel Manczak <203671809+pmanczak@users.noreply.github.com>
|
2026-10-02 12:56:11 +01:00 |
|
|
Simon Danielssonandmergify[bot]
|
98b29aa99a
|
[ROCm][Perf][GLM-5.3-Flash] Add AITER topk backend for decodes (#58167)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-02 11:47:41 +01:00 |
|
|
Chanbin LimandChendi.Xue
|
47de9d4d04
|
[KV Connector][NIXL] Coalesce host-buffer KV copies across cache groups (#54483)
Signed-off-by: beenpow <57864041+beenpow@users.noreply.github.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
|
2026-10-01 13:10:54 -05:00 |
|
|
Rehan KhanandLi, Jiang
|
583637f126
|
[CPU][Perf] Add vectorized Sampler Kernel (#53913)
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-09-30 15:16:28 +08:00 |
|
|
chuan932andMisha Goin
|
f550ad8bf7
|
[Kernel][Perf] Register-resident path for per-token-group 8-bit quant (#55330)
Signed-off-by: chao.huan <chao.huan@nio.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-09-25 08:11:42 -07:00 |
|
|
Yongye ZhuandSummer Yang
|
442bd00d9f
|
[Perf][Distributed] Add low-SM multimem reduce-scatter for SM100/SM103 (#55072)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
Co-authored-by: Summer Yang <girasoleyang@gmail.com>
|
2026-09-25 03:27:21 +00:00 |
|
|
Harry MellorandClaude Opus 5.5
|
d636456b1f
|
[Frontend] Remove the slow tokenizer mode (#58545)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-09-24 08:48:28 -07:00 |
|
|
Misha Goin
|
25965ee583
|
[Kernel] Remove AllSpark INT8 W8A16 GEMM backend (#58001)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-22 14:07:34 -07:00 |
|
|
|
f92b78f6ef
|
[Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-22 01:07:17 -07:00 |
|
|
Harry MellorandClaude Opus 5
|
651a88c09a
|
[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-16 10:57:24 -07:00 |
|
|
Misha Goin
|
1085b64425
|
[Benchmark] Retire stale benchmarks and consolidate RMSNorm (#57083)
Signed-off-by: Misha Goin <mgoin64@gmail.com>
|
2026-09-16 13:21:43 -04:00 |
|
|
Harry MellorandClaude Opus 5
|
8c1557a79c
|
Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <hej.mellor@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-16 16:44:29 +00:00 |
|
|
|
d6a1677d55
|
[Model][DSv4.1] FlashMLA mega attention and the NVFP4 compressed KV cache (#56935)
Signed-off-by: Yongye Zhu <yongye@inferact.ai>
Signed-off-by: 云挚 <ningyunxiao.nyx@antgroup.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <yongye@inferact.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Yunxiao Ning <73625538+foraxe@users.noreply.github.com>
Co-authored-by: AI Assistant <noreply@openai.com>
|
2026-09-16 03:07:50 -07:00 |
|
|
Misha GoinandOpenAI Codex
|
c6fa1f05d1
|
[Perf][Kernel] Add sampled filtering for persistent top-k (#56346)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-15 14:15:59 -07:00 |
|
|
Taneem Ibrahimandmergify[bot]
|
8e08cef46e
|
[Bugfix] Redact credentials from benchmark logs (#56662)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-14 18:58:33 -04:00 |
|
|
|
78e84261ab
|
[Performance] Add Triton kernel for Gemma3n sparse GELU (#48498)
Signed-off-by: BWAAEEEK <jooho414@gmail.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-09-14 07:42:15 +00:00 |
|
|
SurajandClaude Opus 5
|
93e051e290
|
[Bugfix][Benchmark] Make streaming TTFT/E2E latency accounting consistent across endpoints (#55508)
Signed-off-by: surajm20061998 <surajm20061998@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-13 05:20:54 +00:00 |
|
|
Misha Goin
|
8a7f98c8c3
|
[Kernel][MoE] Optimize batched_moe_align_block_size with cooperative writes (#53280)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-11 12:05:22 -07:00 |
|
|
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 |
|
|
Simon Danielsson
|
ae48466cf3
|
[Perf][ROCm] Add AITER custom AG/RS (DP only) (#48247)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
|
2026-09-11 13:19:57 +08:00 |
|
|
Li, Jiang
|
c3ccc0e957
|
[Model] Add DeepSeek-V4 CPU backend (#55355)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-09-10 14:14:48 +08:00 |
|
|
Roderick Wuandmgoin
|
2c9d68f80b
|
[Quant][Kernel] Remove GPTQ Group/Dynamic Activation Ordering (#54809)
Signed-off-by: Roderick-Wu <roderickwu2003@gmail.com>
Signed-off-by: Roderick Wu <roderickwu2003@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-09-08 12:45:12 -07:00 |
|
|
zhao, zhenhui
|
1c344ed41e
|
[CPU] [Feat] Add native AMX-FP8 attention impl for Diamond Rapids (#49410)
Signed-off-by: zhejiangxiaomai <zhenhui.zhao@intel.com>
|
2026-09-06 11:06:56 +08:00 |
|
|
linitra24andJee Jee Li
|
7985444339
|
[Kernel][HY V4] Add Triton iHC pre/post fallback (#55059)
Signed-off-by: linitra24 <renshuang.zhou@daocloud.io>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-05 23:12:50 +08:00 |
|
|
Yongye ZhuandOpenAI Codex
|
3ba9907a1d
|
[Kimi-K3] Overlap low-M TP8 KDA projections (#54697)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-02 03:35:28 +00:00 |
|
|
Yongye Zhu
|
d6d6658543
|
[Kimi-K3][Perf] Make native CUDA AttnRes the SM100 default (#54261)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-08-31 23:18:12 +00:00 |
|
|
Jee Jee Li
|
e2c8eeac40
|
[kernel] Fused embedding kernel (#53677)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-08-31 11:34:14 +00:00 |
|