Commit Graph

7855 Commits

Author SHA1 Message Date
Khoa Pham
cd75d54fc5 [Bugfix] Fix CUDA graph replay issues in trtllm_mla draft_extend (#21987)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-03 01:45:13 -07:00
shuwenn
4f84ce5807 [CI] ci: add test_http_server_auth.py to CI (#21866) 2026-04-03 16:32:18 +08:00
Thomas Wang
7431db7392 [AMD] Enable FP8 KV cache and FP8 attention kernel for NSA on MI300/MI355 with TileLang backend (#21511) 2026-04-03 00:58:23 -07:00
Kelon
ad0516d9c1 [NPU] optimize glm4.7 (#19246) 2026-04-03 15:44:07 +08:00
Shangming Cai
d82097a0df [PD] Tiny register info field cleanup for mooncake backend (#22016) 2026-04-03 15:13:44 +08:00
Ricardo-M-L
24f52e66d3 fix: remove duplicate words in comments (#22007) 2026-04-03 00:05:39 -07:00
Yuzhen Zhou
6b876a7710 [ROCM][RL] Shuffle Weight In-Place to Preserve Parameter Attributes (#21825) 2026-04-02 23:43:55 -07:00
Zhangheng
4d097047f2 [PD]: Add support for HiSparse to directly transfer the cache from Prefill to Decode DRAM. (#21591)
Co-authored-by: Tingwei Huang <huangtingwei9988@gmail.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2026-04-02 23:06:12 -07:00
kk
5bcbc9757c [AMD] Resolve the performance degression when launch server with "--enable-aiter-allreduce-fusion" (#21947)
Co-authored-by: wunhuang <wunhuang@amd.com>
2026-04-02 22:10:24 -07:00
DarkSharpness
d1b7c3907d [Parallel State Refactor 2/n] Unify code path of AMD deterministic all reduce (#20871) 2026-04-03 12:33:17 +08:00
Baizhou Zhang
efa7b2d5d3 Revert "[MUSA][9/N] Add FA3 attention backend support through MATE (MUSA AI Tensor Engine)" (#22002) 2026-04-02 20:42:13 -07:00
lviy
5f0df1e2ad [Bugfix] Fix incorrect dp-attention parallel info in bench_one_batch (#21519) 2026-04-02 20:13:53 -07:00
Yuhao Yang
69e89a1fcc [VLM] Enable per-image MM splitting by default and remove MULTI_IMAGES modality (#21899) 2026-04-03 11:04:41 +08:00
narutolhy
8897ac58f0 [PP] qwen3 vl skip layer id for pp (#19135) 2026-04-03 10:51:53 +08:00
Mook
991f3aa5b3 [Feature] NVFP4 Marlin fallback for non-Blackwell GPUs (SM75+) (#19652) 2026-04-03 10:48:15 +08:00
Khoa Pham
2b5aed94f5 Remove maxItems=1 restriction when tool_choice is specified (#20208) 2026-04-03 02:35:24 +00:00
Thomas
0539c62bc1 [Diffusion][NPU] Add support for MOVA (#21633)
Co-authored-by: zhangshuai (S) <z00836796@china.huawei.com>
2026-04-03 05:33:14 +03:00
Kangyan-Zhou
1f97714f9b [CI] Add timeouts to Slack upload urlopen and WebClient (#21903)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 19:30:55 -07:00
Xiaoyu Zhang
89affff290 Skip broken AutoModel mapping entries when resolving Llava submodules (#21892) 2026-04-03 09:04:26 +08:00
Adarsh Shirawalmath
34ddf135fd [Feature] Stronger transformers modeling backend with TP, PP, MoE, VLMs, and torch compile (#19163) 2026-04-02 16:02:33 -07:00
ori
939cf398a9 [MUSA][9/N] Add FA3 attention backend support through MATE (MUSA AI Tensor Engine) (#17985)
Co-authored-by: R0CKSTAR <xiaodong.ye@mthreads.com>
2026-04-02 15:04:31 -07:00
Ethan (Yusheng) Su
566b4a4f1c [4/n] Support gpt oss 20b lora (#21570) 2026-04-02 12:57:38 -07:00
Lianmin Zheng
fe38410c3e Remove logging for subprocess watchdog start (#21968) 2026-04-02 11:30:33 -07:00
Feng Su
8732b2e9c6 [CI] [Tracing] Add ci for tracing and fix bugs (#21740) 2026-04-02 10:50:50 -07:00
Mick
2278a321ca [diffusion] chore: fix stage profiler for multi-stage denoising (#21955) 2026-04-03 01:16:38 +08:00
DarkSharpness
df94cdcebb [Parallel State Refactor 1/n] Remove stream of PyNCCL (#20866) 2026-04-03 00:47:50 +08:00
Ke Bao
b21db86e2f [CI] Fix gpu deps import in cpu test (#21950) 2026-04-03 00:06:31 +08:00
Todobe
083304ca44 [NPU] Support GLM-4.7-Flash on NPU (#21408) 2026-04-02 17:44:50 +08:00
Liangsheng Yin
9d9537fbd3 Migrate ngram corpus from torch cpp_extension to TVM FFI jit_kernel (#21920)
Co-authored-by: DarkSharpness <2040703891@qq.com>
2026-04-02 02:18:11 -07:00
Qiaolin Yu
b684b0b72f Fix spec v2 + logprob when max_num_token is set (#20799) 2026-04-02 01:55:16 -07:00
Baizhou Zhang
fbc1f92453 [DSA] Set trtllm kernels as nsa default for Blackwell (#21914) 2026-04-02 00:22:27 -07:00
Yilong Zhao
f30df723bf scheduler: add prefill-only update in merge batch (#21840) 2026-04-01 23:33:06 -07:00
Trevor Morris
d24ea24e18 [NVIDIA] Enable fp8 flashinfer_trtllm_routed MoE for MiniMax-M2.5 (#20394) 2026-04-01 23:02:06 -07:00
Khoa Pham
f836658077 [Spec][Ngram] 4/N: Remove max_match_window_size and min_match_window_size, matching all suffixes of the Trie (#21225) 2026-04-01 22:09:46 -07:00
Liangsheng Yin
269589ad71 Return HTTP 400 for streaming validation errors (#21900) 2026-04-01 21:58:12 -07:00
Khoa Pham
153359b4dd Multi tool streaming fix (#20004) 2026-04-01 21:53:05 -07:00
Mook
7a59e05dd1 [Kernel] Fuse temperature + softmax in sampling for decode speedup (#20501) 2026-04-02 12:46:36 +08:00
Brayden Zhong
cb0c2cbfdb Enable multi-thread weight loading by default (#20289) 2026-04-01 21:27:20 -07:00
Zhangheng
fae66b4050 Support PP key for file backend (#21901) 2026-04-02 12:23:58 +08:00
David Cheung
ed427e1299 Migrate all callers from /get_server_info to /server_info (#21463) 2026-04-01 21:17:50 -07:00
Prozac614
24997fe42c [diffusion] CI: add initial nvfp4 ci test for b200 (#21767)
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-04-02 11:31:08 +08:00
Yuhao Yang
2ef12073f4 [VLM] Add VLM TP=4 per-commit CI test and improve MMMU eval prompt/parser (#21841) 2026-04-01 20:09:47 -07:00
Hanlin Bi
0f6bedf6ed fix pcg torch dynamo recompile in mxfp8 Triton path (#21888)
Co-authored-by: Hanlin Bi <hanlinbi@umich.edu>
2026-04-02 01:57:49 +00:00
Noa Neria
8d9145d97e Direct model loading from object storage with Runai Model Streamer (#17948)
Signed-off-by: Noa Neria <noa@run.ai>
2026-04-01 18:41:22 -07:00
huangtingwei
6dd2f774de [HiCache & PD]Fixed detailed cache hit breakdown in PD scenarios. (#21764) 2026-04-01 17:44:55 -07:00
shuwenn
9cb362f70e [HiCache] fix: Clone host indices to avoid memory leak (#21624)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2026-04-01 17:42:07 -07:00
Liangsheng Yin
d7256eb69a Unify GSM8K eval path to Chat API for regression CI readiness (#21667) 2026-04-01 17:12:19 -07:00
ishandhanani
1081a25983 revert: remove TTL-based hard pin from HiRadixCache (#21884) 2026-04-01 16:51:15 -07:00
Alison Shao
1ac74e652e [Misc] Fix comparator e2e tests: add polars dep + fix dp-attention test (#21804)
Co-authored-by: Alison Shao <alison.shao@mac.lan>
2026-04-01 15:44:35 -07:00
YAMY
821a8a99fb [Disagg] GPU staging buffer with dynamic ring allocator for heterogeneous TP KV transfer (#19890) 2026-04-01 14:09:18 -07:00