|
|
0470cac520
|
updaed
Signed-off-by: Robert Shaw <robshaw@redhat.com>
|
2025-08-14 02:14:03 +00:00 |
|
|
|
0ca2393b47
|
[CI/Build] Increase pooling tolerance to pass CI (#22844)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-08-13 18:52:48 -04:00 |
|
|
|
31a500c86f
|
[Core] [N-gram SD Optimization][1/n] Propose tokens with a single KMP (#22437)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
|
2025-08-13 14:44:06 -07:00 |
|
|
|
df0e0f023e
|
[CI/Build] Skip gpt_big model test because of broken HF model (#22848)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-08-13 20:36:28 +00:00 |
|
|
|
b4b78d6317
|
[CI/Build] Fix param mismatch in test_eagle_correctness (#22847)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-08-13 10:55:25 -07:00 |
|
|
|
12817a8ac7
|
[CI] Fix tests/v1/e2e/test_kv_sharing_fast_prefill.py import on test (#22815)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-13 10:35:50 -07:00 |
|
|
|
c9232d41f4
|
[CI/Build] Update VLM common tests (#22841)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-08-13 10:03:05 -07:00 |
|
|
|
19b927e52d
|
[Core] Use individual MM items in P0/P1 cache and model runner (#22570)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-08-13 07:18:07 -07:00 |
|
|
|
6b794c756c
|
[Nixl][CI] Fix tests (#22806)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-13 06:03:53 -07:00 |
|
|
|
653124bd46
|
[Frontend] Add chunked processing to handle long inputs in embedding models (#22280)
Signed-off-by: x22x22 <wadeking@qq.com>
Signed-off-by: Kdump <rootshellexp@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Maximilien de Bayser <maxdebayser@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-08-13 04:14:24 -07:00 |
|
|
|
d94e3026de
|
[V1] Add tree drafting tests for eagle spec decoding (#22705)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
|
2025-08-13 04:11:28 -07:00 |
|
|
|
a01e0018b5
|
[Bugfix] Fix Nemotron VL image processing (#22739)
Co-authored-by: ducviet00-h2 <viet.d.hoang@h2corporation.jp>
|
2025-08-13 03:11:36 -07:00 |
|
|
|
4c558cf62e
|
[Perf] Support topk softmax fused kernel for broader num_experts (#22211)
Signed-off-by: Shixian Cui <shixian@amazon.com>
Co-authored-by: Shixian Cui <shixian@amazon.com>
|
2025-08-12 21:34:47 -07:00 |
|
|
|
c5830381af
|
[V0 Deprecation] Remove args for multi-step scheduling (#22779)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
|
2025-08-12 20:38:18 -07:00 |
|
|
|
d31f97cf57
|
[Misc] Remove tests/multi_step/__init__.py (#22778)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
|
2025-08-12 20:21:18 -07:00 |
|
|
|
71683ca6f6
|
[V0 Deprecation] Remove multi-step scheduling (#22138)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
|
2025-08-12 20:18:39 -07:00 |
|
|
|
53c730286c
|
[Misc] parametrize 'dtype' in test_flash_mla (#22641)
Signed-off-by: RUTHLESS-BOT <wujiafeng@cmbchina.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-08-12 16:31:48 -04:00 |
|
|
|
422f22e012
|
[CI][Nixl] Check kv cache layout during handshake (#22745)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-12 12:53:52 -07:00 |
|
|
|
c42fe0b63a
|
Add more test scenario for tensor schema (#22733)
Signed-off-by: teekenl <teekenlau@gmail.com>
|
2025-08-12 16:34:41 +00:00 |
|
|
|
5a4b4b3729
|
Add: SupportsEagle3 interface for explicit EAGLE3 support (#22642)
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
|
2025-08-12 09:24:52 -07:00 |
|
|
|
3d9d40efde
|
[Bugfix][CI] Fix test_remote_decode_lifecycle.py::test_short_prompt_lifecycle (#22727)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-08-12 07:30:17 -07:00 |
|
|
|
80bb1e8afe
|
Officially support SmolLM3 using the Transformers backend (#22665)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-08-12 05:38:48 -07:00 |
|
|
|
007dd90859
|
[gpt-oss] Enable gpt-oss on ampere (#22714)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2025-08-12 03:21:44 -07:00 |
|
|
|
46ae7f6666
|
[Bugfix] Mamba2 SSD varlen bug fix initstates decay, improve test, assert chunk pwr 2 (#21783)
Signed-off-by: Rishi Astra <40644327+RishiAstra@users.noreply.github.com>
|
2025-08-12 02:04:37 -07:00 |
|
|
|
bc8372efc3
|
[Bugfix] Fix erroneous randomly generated cases in bad word testing (#22170)
Signed-off-by: phantomlei <phantomlei3@gmail.com>
|
2025-08-12 02:03:22 -07:00 |
|
|
|
9f909b8996
|
[New Model] Support Command-A-Vision (#22660)
Signed-off-by: donglu <donglu@cohere.com>
|
2025-08-12 01:39:54 -07:00 |
|
|
|
6d729c43fb
|
[Bugfix] Fix ModernBert load & Enable sliding window attention for bidirectional attention. (#22637)
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
|
2025-08-12 00:23:17 -07:00 |
|
|
|
93d0652433
|
[CI] Increase timeout for test_completion_with_image_embeds (#22670)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-11 20:31:36 -07:00 |
|
|
|
ea1292ad3e
|
[CI Failure] Use float32 for tests/entrypoints/openai/test_audio.py (#22686)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2025-08-11 20:20:42 -07:00 |
|
|
|
839ab00349
|
Re-enable Xet on TPU tests now that hf_xet has been updated (#22666)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-08-11 19:54:40 -07:00 |
|
|
|
1891a265d3
|
[gpt-oss] Add test for response API + harmony (but skipped) (#22554)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-08-11 17:47:24 -07:00 |
|
|
|
65abe111a3
|
[CI] Skip Tree Attn Test in test_max_len.py to unblock CI (#22664)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-08-11 10:36:05 -07:00 |
|
|
|
807d21b80d
|
[BugFix] [Spec Decode] Remove LlamaForCausalLMEagle3 to fix CI (#22611)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
|
2025-08-11 10:31:36 -07:00 |
|
|
|
c90fb03df5
|
[CI/Build] Skip Mllama HF runner tests with Transformers v4.55.0 (#22659)
Signed-off-by: Isotr0py <2037008807@qq.com>
|
2025-08-11 10:00:58 -07:00 |
|
|
|
84cf78acee
|
[Model] Pooling models default to using chunked prefill & prefix caching if supported. (#20930)
Signed-off-by: wang.yuqi <noooop@126.com>
|
2025-08-11 09:41:37 -07:00 |
|
|
|
16fb668b61
|
fix: NIXL connector transfers partial block to pass full multi-modal context (#21074)
Signed-off-by: GuanLuo <gluo@nvidia.com>
|
2025-08-11 09:40:55 -07:00 |
|
|
|
f7dcce7a4a
|
[Feature] Add VLLM_USE_DEEP_GEMM_E8M0 Env to Control E8M0 Scale (#21968)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-08-11 09:39:08 -07:00 |
|
|
|
ebf7605b0d
|
[Misc] Move tensor schema tests (#22612)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-08-11 00:15:27 -07:00 |
|
|
|
39052dbca8
|
Support token_type_ids in V1 with less code changes (#21985)
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
|
2025-08-10 22:54:59 -07:00 |
|
|
|
5898b135ab
|
[BugFix] Fix KVConnectorOutput TPU breakage (#22598)
Signed-off-by: Nick Hill <nhill@redhat.com>
|
2025-08-10 19:33:48 -07:00 |
|
|
|
b799f4b9ea
|
[CI/Build] Fix tensorizer test for load_format change (#22583)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
|
2025-08-10 19:30:00 -07:00 |
|
|
|
68b254d673
|
Fix TensorSchema validation test for symbolic dims (#22366)
Signed-off-by: Benji Beck <benjibeck@meta.com>
|
2025-08-10 17:16:44 +00:00 |
|
|
|
b76753f0b5
|
[Bugfix][Kernel] Support partial rotary embedding for MRoPE triton kernel (#22593)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-08-10 09:00:36 -07:00 |
|
|
|
049c245143
|
[Misc] Replace flaky image urls in pixtral test (#22574)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
|
2025-08-10 06:18:21 -07:00 |
|
|
|
326976291b
|
[Misc] code clean duplicate set_current_vllm_config in _set_vllm_config (#22566)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
|
2025-08-10 00:08:48 -07:00 |
|
|
|
c49848396d
|
Refactor sliding window configuration to Transformers best practice (#21927)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-08-09 20:50:48 -07:00 |
|
|
|
2a84fb422f
|
[TPU] kv cache update kernel doesn't need to be padded slices to multiple of num_slices_per_block (#22394)
Signed-off-by: Chengji Yao <chengjiyao@gmail.com>
Co-authored-by: Chengji Yao <chengjiyao@gmail.com>
|
2025-08-09 20:49:04 -07:00 |
|
|
|
3d7363e61c
|
[Config] add "qwen" as a native eagle3 target supported model (#22333)
Signed-off-by: lechen <lecself@163.com>
Signed-off-by: LeChen <lecself@163.com>
|
2025-08-09 20:21:05 -07:00 |
|
|
|
61f67d8acd
|
[V1] [Hybrid] Enable Full CUDA Graph (decode-only) for Mamba layers (#21401)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
|
2025-08-09 20:16:11 -07:00 |
|
|
|
42172ad18f
|
[FEAT] [Performance] Add triton mrope to replace the torch code path (#22375)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-08-09 11:50:03 -07:00 |
|
