 Srinivas Krovvidiandsrinivas_oo7
|
091bc1026e
|
[KV Offloading] Add tiering metric plumbing (#45959)
Signed-off-by: srinivas_oo7 <sklinkedin0120@gmail.com>
Co-authored-by: srinivas_oo7 <sklinkedin0120@gmail.com>
|
2026-06-23 15:10:36 +03:00 |
|
|
hillel.darshanandCursor
|
3554ada5d8
|
[CPU][Bugfix][Speculative Decoding] Accept USE_FP64_GUMBEL in CPU recovered-tokens sampler (#46069)
Signed-off-by: hillel.darshan <hillel.darshan@intel.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-23 11:54:07 +00:00 |
|
|
wang.yuqi
|
31ca9504b1
|
[Frontend] Split ServingRender into renderer and entrypoint. (#44285)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-06-23 11:19:09 +00:00 |
|
|
|
d32575a2d2
|
[ROCm][P/D] Support MoRIIO heterogeneous TP fan-in (#46332)
Signed-off-by: Tan Pin Siang <tanpinsiang@gmail.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Jun Kang Chow <junkangchow@gmail.com>
Co-authored-by: Chun Fang <chun.fang@amd.com>
Co-authored-by: TianDi101 <ditian12@amd.com>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-06-23 10:33:23 +00:00 |
|
|
Juan Pérez de Algaba
|
83fa302ca4
|
fix(security): prevent infinite loop in split_audio with NaN audio sa… (#46463)
|
2026-06-23 10:24:51 +00:00 |
|
|
frida-andersson
|
20b5af55c1
|
[ROCm][Perf] DSv3.2: fuse MLA Q concat+fp8-quant in forward_mqa (#43673)
Signed-off-by: Frida Andersson <fanderss@amd.com>
|
2026-06-23 18:12:04 +08:00 |
|
|
Qiming Zhang
|
901a3b091c
|
fix gpt_oss pp>1 with ep (#46441)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-06-23 16:59:11 +08:00 |
|
|
ReidandBugen Zhao
|
2d721ab5d8
|
[Rust Frontend] Align Rust allowed_token_ids validation with Python (#46348)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-23 08:32:33 +00:00 |
|
|
Reidandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
accaa434f3
|
[Rust Frontend] Support echo for token-ID completion prompts (#46219)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
|
2026-06-23 08:04:41 +00:00 |
|
|
Sunny Yuan
|
a04654da23
|
Doc: fix missing GLM-5.x in supported models (#46452)
Signed-off-by: Sunny Yuan <y.zichen@wustl.edu>
|
2026-06-23 07:42:27 +00:00 |
|
|
Bugen Zhao
|
25bc3be49c
|
[Rust Frontend] Correct --reasoning-parser semantics (#46359)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-23 15:38:39 +08:00 |
|
|
Ting SUN
|
a46f3eb232
|
[Bugfix][Model Runner V2] Preserve all allowed_token_ids in the logit bias kernel (#46245)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
|
2026-06-23 07:01:13 +00:00 |
|
|
|
6c427dd401
|
[BugFix] Omit empty tool_calls from OpenAI chat responses (#44105)
Signed-off-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
|
2026-06-23 13:43:53 +08:00 |
|
|
Chaunceyandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
3ce5823762
|
[Refactor] Responses API parser state into conversation context (#46030)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-23 13:42:58 +08:00 |
|
|
Woosuk Kwon
|
04c2a8deac
|
[DeepEP V2] Fill invalid recv_topk_idx with -1 (#46432)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-06-22 21:45:49 -07:00 |
|
|
|
7e47fb72b5
|
[ROCm][P/D] Fix MoRIIO WRITE mode for mixed KV layouts (#46290)
Signed-off-by: Tan Pin Siang <tanpinsiang@gmail.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Jun Kang Chow <junkangchow@gmail.com>
Co-authored-by: Chun Fang <chun.fang@amd.com>
Co-authored-by: TianDi101 <ditian12@amd.com>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
|
2026-06-23 12:12:51 +08:00 |
|
|
Bugen Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
a8481be7a9
|
[Rust Frontend][Perf] Use dedicated runtime for HTTP/request-processing/ZMQ (#46051)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-23 04:03:20 +00:00 |
|
|
Kunshang Ji
|
9d3317172c
|
[XPU][CI]fix xpu kv cache layout test (#46429)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-06-23 03:43:29 +00:00 |
|
|
Dao007foreverandClaude Opus 4.8
|
430a95ae3a
|
[v1][kvcache] Honor prefix-cache retention interval for Mamba/linear attention (#45845)
Signed-off-by: Dao Le <daole@inferact.ai>
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-22 19:51:11 -07:00 |
|
|
Mike G
|
56e5797511
|
[Quant] Enable modelopt_mixed on Turing (SM75) (#45375)
Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>
|
2026-06-22 19:30:49 -07:00 |
|
|
Rui Yinandabinggo
|
8db12169a4
|
fix: stream Qwen3 tool call string arguments (#46351)
Signed-off-by: Rui Yin <2260891073@qq.com>
Co-authored-by: abinggo <107740309+abinggo@users.noreply.github.com>
|
2026-06-23 10:26:37 +08:00 |
|
|
MichaelCaooandClaude
|
33f50773cb
|
[Doc] Fix typos, grammar, and broken commands across docs (#46398)
Signed-off-by: MichaelCaoo <a992033227@163.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-23 02:01:22 +00:00 |
|
|
Micah Williamson
|
fa36f86d77
|
[CI] Torch 2.11 flaky test_spec_decode_logprobs and gritlm tests (#45772)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-06-23 01:26:54 +00:00 |
|
|
Michael GoinandClaude Opus 4.8
|
8207ce0850
|
[Bugfix] Fix humming lm_head crash and FusedMoE weight_shape coercion (#46420)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-22 18:19:29 -07:00 |
|
|
|
e48592066e
|
[DeepEP V2] Bound num_max_tokens_per_rank in do_expand=False (#46404)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Roy Wang <jasonailu87@gmail.com>
Co-authored-by: gnovack <novackgm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-22 18:14:53 -07:00 |
|
|
stefankoncarevicandAndreas Karatzas
|
91ba720b75
|
[ROCm][CI] Only require q_scale==1.0 for fp8 query in RocmAttention (#46148)
Signed-off-by: stefankoncarevic <stefan.koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-22 18:25:43 -05:00 |
|
|
fxmarty-amd
|
6ead164e52
|
[CI] Add TP=4 requirement to test_mixed_precision_model_accuracies (#46161)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-06-22 18:19:43 -05:00 |
|
|
Bowen BaoandAndreas Karatzas
|
c97e8f99d6
|
[ROCm][Quantization][4/N] refactor quark_moe fp8 w/ oracle (#43721)
Signed-off-by: Bowen Bao <bowenbao@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-22 15:58:03 -07:00 |
|
|
|
183b5f27ea
|
[Bugfix][V1][TurboQuant] Reserve workspace before CUDA graph capture (#44053)
Signed-off-by: Guipeng Zhang <zhangguipeng23z@ict.ac.cn>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-06-22 15:47:48 -07:00 |
|
|
ZewenShen-Cohereandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
ca5b24695b
|
Fix static actorder handling for compressed-tensors WNA16 MoE (#41161)
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-22 15:46:46 -07:00 |
|
|
Charlie Fu
|
6f6bd3b8fe
|
[ROCm][CI] Increase the max wait time for server startup (#46417)
Signed-off-by: charlifu <charlifu@amd.com>
|
2026-06-22 17:46:31 -05:00 |
|
|
Andreas Karatzas
|
70ef4d3009
|
[ROCm][CI] Purging away redundant test group definitions (#46418)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-22 15:42:47 -07:00 |
|
|
Tyler Michael SmithandClaude
|
e2fe837572
|
[CI] Fix CPU-Multi-Modal Model Tests timeout by adding a 4th shard (#46388)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-22 22:08:00 +00:00 |
|
|
Aarushi Jain
|
fbf9ff7cf4
|
[CI][ROCm] Restrict MLA cross-layer KV cache test to supported backends on ROCm (#46401)
Signed-off-by: aarushjain29 <Aarushi.Jain2@amd.com>
|
2026-06-22 17:05:26 -05:00 |
|
|
Michael GoinandClaude Opus 4.8
|
6cc2c9ba3a
|
[CI] Add DGX Spark GPQA smoke test (#39541)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-22 14:52:38 -07:00 |
|
|
|
c0b2d8f471
|
[Bugfix] FusedMoE: coerce shape-(1,) per-tensor scales to 0-D scalar … (#43362)
Signed-off-by: Varshith <kvarshithgowda@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-06-22 13:26:53 -07:00 |
|
|
Mohammad Miadh Angkad
|
d1a38c2762
|
[Kernel][Performance] Add FlashInfer cutedsl NVFP4 GEMM backend (#42235)
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-06-22 16:17:18 -04:00 |
|
|
stefankoncarevicandAndreas Karatzas
|
2b4a7491ec
|
[ROCm][CI] Query total device memory via amdsmi to avoid HIP init (#46141)
Signed-off-by: stefankoncarevic <stefan.koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-22 15:12:24 -05:00 |
|
|
Saddss
|
82ede09a5a
|
[Bugfix][KVConnector] Fix SimpleCPUOffloadConnector GPU->CPU store race (#46278)
|
2026-06-22 13:08:47 -07:00 |
|
|
Nick Hill
|
fbf520cf3a
|
[MRV2] Generalize use of WhisperModelState (#46096)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-06-22 12:40:02 -07:00 |
|
|
|
44d95069e9
|
Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-06-22 11:54:14 -07:00 |
|
|
Dao007foreverandClaude Opus 4.8
|
3ce15fd574
|
[v1][kvconnector] DecodeBenchConnector: fill list/tuple (Mamba/KDA) KV caches (#45080)
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-22 11:54:00 -07:00 |
|
|
Jinzhen Linandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
e4b3da3feb
|
[Quantization][CI] add humming lm-eval test (#43752)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-22 11:23:55 -07:00 |
|
|
|
3e6529cc0e
|
[Bugfix][Spec Decode] Fix EAGLE drafter multimodal encoder cache misses (#46315)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-06-22 18:14:02 +00:00 |
|
|
Ilya MarkovandMarkov Ilya
|
ac614587f5
|
[EPLB] Enable nixl eplb communicator for elastic ep (#45013)
Signed-off-by: Markov Ilya <markovilya197@gmail.com>
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Markov Ilya <markovilya19@gmail.com>
|
2026-06-22 10:54:08 -07:00 |
|
|
Taneem Ibrahimandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
f2069b005b
|
[Pooling] Validate non-negative rerank top_n (#46119)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-22 11:40:47 -04:00 |
|
|
Martin Hickey
|
ccd49f6821
|
[MyPy] Fix mypy for vllm/lora (#41722)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
|
2026-06-22 10:57:09 -04:00 |
|
|
Li, Jiang
|
1c7bc18318
|
[Bugfix][CPU] Fix CPU model runner v2 (#46365)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-06-22 22:52:05 +08:00 |
|
|
AlexHuang
|
9a938df64e
|
[Test][KV Offloading] Add unit tests for OffloadingSpecFactory and SecondaryTierFactory (#46355)
Signed-off-by: Alex <alex.tech.lab@outlook.com>
|
2026-06-22 17:45:04 +03:00 |
|
|
Liangliang Ma
|
3da4a1b124
|
[XPU] add awq format for INCXPULinear (#43404)
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
|
2026-06-22 22:29:13 +08:00 |
|