Commit Graph

81 Commits

Author SHA1 Message Date
Cheng Wan
cb099d2095 [CUDA Graph] save cuda graph memory by using next_token_logits_buffer (#8579) 2025-08-03 03:06:47 -07:00
Cheng Wan
e236d8fee8 Save peak memory in logits processor (#8343) 2025-07-26 01:46:42 -07:00
Cheng Wan
c0fb25e949 DP Enhancement (#8280) 2025-07-24 21:36:21 -07:00
Cheng Wan
cb432f1770 saving hidden_states.clone() (#7705) 2025-07-04 20:07:42 -07:00
Chunyuan WU
9fcc9a80e7 [CPU] refine CPU integration code (#7647) 2025-07-03 09:51:09 -07:00
Chunyuan WU
7eb47b0f3d [CPU] [BF16] Call fused_experts_cpu, weight_packed_linear and bmm_cpu kernel in DeepSeek model (#6641)
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
2025-06-25 01:43:33 -07:00
Cheng Wan
e879d8b7a8 [Feature] Comprehensive Hybrid Parallelism Support (#6389) 2025-06-20 14:43:11 -07:00
Neo
0ca594eda9 [FIX]remove redundant code in logits_processor.py (#7079) 2025-06-11 11:49:30 -07:00
Cheng Wan
b2e95f62b4 Fix two issues related to --moe-dense-tp-size=1 (#5657)
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
Co-authored-by: 颉沆 <xiehang.lsy@alibaba-inc.com>
2025-05-12 23:51:39 -07:00
Lianmin Zheng
e8e18dcdcc Revert "fix some typos" (#6244) 2025-05-12 12:53:26 -07:00
applesaucethebun
d738ab52f8 fix some typos (#6209)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
2025-05-13 01:42:38 +08:00
Cheng Wan
25c83fff6a Performing Vocabulary Parallelism for LM Head across Attention TP Groups (#5558)
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
2025-05-11 23:36:29 -07:00
aoshen524
9ad28f639e fix(srt): check if sample_indices is not None before usage. (#5633) 2025-04-26 19:51:01 -07:00
Cheng Wan
3196999f63 Reduce computation and communication in DP attention (#4521) 2025-03-18 13:41:36 -07:00
James Liu
9e0186f352 [Feature] Support EAGLE 3 (#4247) 2025-03-18 07:35:23 -07:00
Lianmin Zheng
8e66fbecee Improve DP attention (#4390)
Co-authored-by: dhou-xai <dhou@x.ai>
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
2025-03-13 08:23:56 -07:00
Qubitium-ModelCloud
56a724eba3 [QUANT] Add GPTQModel Dynamic Quantization + lm_head Quantization (#3790)
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Co-authored-by: ZX-ModelCloud <zx@modelcloud.ai>
2025-03-05 01:11:00 -08:00
Lianmin Zheng
e074d84e5b [Minor] more code cleanup (#4077) 2025-03-04 21:23:47 -08:00
Qubitium-ModelCloud
87f671ab58 Fix debug_tensor_dump_output_folder optional key missing (#4046) 2025-03-04 03:42:48 -08:00
Lianmin Zheng
66301e124f Improve code styles (#4021) 2025-03-03 03:20:23 -08:00
Lianmin Zheng
ac2387279e Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: dhou-xai <dhou@x.ai>
Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>
2025-03-03 00:12:04 -08:00
Lianmin Zheng
3d8f1c9bcf Use int64 as indices for set_kv_buffer (#3039) 2025-01-21 19:46:09 -08:00
Lianmin Zheng
23196d5254 Simplify logits processor (#2974)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
2025-01-18 23:03:49 -08:00
Mick
3d93f84a00 [Feature] Support minicpmv v2.6 (#2785)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: yizhang2077 <1109276519@qq.com>
2025-01-18 14:14:19 -08:00
Yineng Zhang
5dc54f1a62 feat: remove vllm distributed (#2907)
Co-authored-by: Zhangyi <1109276519@qq.com>
2025-01-17 22:31:51 +08:00
Lianmin Zheng
8b6ce52e92 Support multi-node DP attention (#2925)
Co-authored-by: dhou-xai <dhou@x.ai>
2025-01-16 11:15:00 -08:00
Lianmin Zheng
f65c13b559 Remove normalized_prompt_logprobs from the engine to make code easier to maintain (#2902) 2025-01-15 04:54:14 -08:00
Lianmin Zheng
bdc1acf6cd Misc fix for min_p_sampling, --cuda-graph-bs (#2761) 2025-01-07 02:52:53 -08:00
Lianmin Zheng
b8574f6953 Clean up eagle code (#2756) 2025-01-06 14:54:18 -08:00
Lianmin Zheng
b0524c3789 Eagle speculative decoding part 2: Fix cuda graph + DP attention hanging (#2684)
Co-authored-by: yukavio <kavioyu@gmail.com>
2024-12-31 02:25:05 -08:00
Lianmin Zheng
21ec66e59e Minor follow-up fixes for the logprob refactor (#2670) 2024-12-30 05:42:08 -08:00
Lianmin Zheng
9c6ba2484f Refactor logprob computation to return the real logprob used in sampling (#2664) 2024-12-30 04:51:38 -08:00
Lianmin Zheng
3815b23ccb Clean up wrapper in flashinfer backend (#2638) 2024-12-29 00:45:57 -08:00
Lianmin Zheng
7a1aecb938 Simplify pytorch sampling kernel and logit processor (#2491) 2024-12-16 14:11:09 -08:00
Fred Reiss
993956c6b1 Add support for IBM Granite 3.x models (#2437) 2024-12-11 06:30:23 -08:00
Lianmin Zheng
a6ca736c8e Simplify stream_output (#2398) 2024-12-08 12:27:13 -08:00
Lianmin Zheng
4936be8acc Revert "Revert "[FEAT] Support GGUF format"" (#2287) 2024-11-30 22:14:48 -08:00
Lianmin Zheng
7e4c6dd8da Revert "[FEAT] Support GGUF format" (#2285) 2024-11-30 19:03:26 -08:00
Yang Zheng
883c955489 [FEAT] Support GGUF format (#2215)
Co-authored-by: Yang Zheng(SW)(Alex) <you@example.com>
2024-11-30 00:44:48 -08:00
Xuehai Pan
62a4a339eb docs: fix module docstrings and copyright headers (#2077) 2024-11-22 22:16:53 +08:00
Lianmin Zheng
edad373135 Fix illegal memory access in overlap mode & Use more fused triton kernels for building meta data (#2051) 2024-11-16 16:14:23 -08:00
Lianmin Zheng
e646c5901e Fix logprob in the overlapped mode (#1795) 2024-10-25 11:06:57 -07:00
Lianmin Zheng
63ba2f8d7b Clean up batch data structures: Introducing ModelWorkerBatch (#1544) 2024-09-30 06:41:49 -07:00
Lianmin Zheng
36d5acfca5 Rename InputMetadata -> ForwardBatch (#1543) 2024-09-30 02:41:11 -07:00
Lianmin Zheng
9ba1f09760 [Fix] Fix logprob and normalized_logprob (#1428) 2024-09-15 06:36:06 -07:00
Liangsheng Yin
69b3bb9ae1 Unify forward mode (#1360) 2024-09-09 13:49:29 -07:00
Liangsheng Yin
381dd57bd6 Sampler cudagraph (#1253) 2024-08-28 18:58:52 -07:00
Yineng Zhang
f25f4dfde5 hotfix: revert sampler CUDA Graph (#1242) 2024-08-28 21:16:47 +10:00
Liangsheng Yin
75ce37f401 Move sampler into CUDA graph (#1201)
Co-authored-by: Yineng Zhang <me@zhyncs.com>
2024-08-26 07:02:50 -07:00
Lianmin Zheng
f6af3a6561 Cleanup readme, llava examples, usage examples and nccl init (#1194) 2024-08-24 08:02:23 -07:00