Commit Graph
51 Commits
Author SHA1 Message Date
Mick a1f011d09a minor: determine mm attn backend based on platforms (#9303) 2025-08-22 01:08:41 -07:00
Mick ef3004d90a misc: parse bench_serving result as markdown table (#9377) 2025-08-20 16:44:20 -07:00
Mick 1df84ff414 ci: simplify multi-modality tests by using mixins (#9006) 2025-08-16 22:25:02 -07:00
Mick 584e1ab2d0 fix: fix unsupported palette mode of images in bench_serving for mmmu (#9206) 2025-08-14 18:44:46 -07:00
Mick 41d71ca488 fix: fix obsolete qwen-audio processor arg (#9003) 2025-08-09 13:18:36 -07:00
Mickandzhyncs 01c99a9959 chore: update Dockerfile (#8872)
Co-authored-by: zhyncs <me@zhyncs.com>
2025-08-06 09:30:33 -07:00
MickandXinyuan Tong 1992ef9ba7 fix: temporarily disable cuda-ipc for mm data tensor (#8431)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-07-29 22:42:03 +00:00
Mick 0bcc195f4e fix: minor fix TransportProxyTensor under tp (#8382) 2025-07-27 00:38:49 -07:00
MickandXinyuan Tong 3212c2ad3f vlm: optimize tensor transport (#6003)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2025-07-26 17:41:01 +08:00
Mick 534756749a chore: improvements on mm_utils (#7737) 2025-07-26 17:38:56 +08:00
MickandXinyuan Tong 4fa44d63c6 chore: improve mmmu benchmark (#7000)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-07-26 16:19:45 +08:00
Mick 3964b352c3 chore: tune mem fraction static for vlm (#6881) 2025-07-18 17:19:27 -07:00
Mick e1020dc588 refactor: simply MultimodalTokens logic (#7924) 2025-07-17 17:59:15 -07:00
Mick 4395c87a9b refactor: unify names of the feature field of MultimodalDataItem (#8075) 2025-07-16 17:52:38 -07:00
Mick 497efe747d Revert "feat: replace Decord with video_reader-rs" (#8077) 2025-07-15 20:04:56 -07:00
Mick b5e3d6031c vlm: support video as an input modality (#5888) 2025-07-09 23:48:35 -07:00
Mick 199d621845 ci: fix port args (#7792) 2025-07-05 15:06:42 -07:00
Mick c797322280 fix: fix apply_shuffle_mul_sum (#7444) 2025-07-04 23:23:30 -07:00
Mick 4d67025a1d chore: improve ci bug reporting (#7542) 2025-06-26 01:32:44 -07:00
Mick 83d87685c5 vlm: adapt internvl to VisionAttention (#6870) 2025-06-11 01:16:04 -07:00
Mick ce9d690ef4 fix: fix nightly test from updating transformers (#6658) 2025-05-27 00:28:11 -07:00
Mick 626ccb7d3f vlm: tensor hash kernel (#5974) 2025-05-18 15:38:16 -07:00
Mick 01dd39bac1 refactor: minor refactors regarding multimodal processing (#6187) 2025-05-17 22:53:20 -07:00
cd7c8a8de6 doc: update developer guide regarding mllms (#6138)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: XinyuanTong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
2025-05-14 23:13:13 +08:00
Mick 02723e1b0d CI: rewrite test_vision_chunked_prefill to speedup (#5682) 2025-04-26 18:33:13 -07:00
feda9b11b3 fix: fix one more bug from merging mm_inputs (#5718)
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: XinyuanTong <115166877+JustinTong0323@users.noreply.github.com>
2025-04-25 17:28:33 -07:00
MickandXinyuan Tong c998d04b46 vlm: enable radix cache for qwen-vl models (#5349)
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
2025-04-23 20:35:05 -07:00
Mick 34ef6c8135 [VLM] Adopt fast image processor by default (#5065) 2025-04-11 21:46:58 -07:00
Mick e53a0b3d5b [fix] fix mrope positions not picked up (#5265) 2025-04-11 01:29:45 -07:00
Mick fbebcb7aa4 model: support mllama4 (#5144) 2025-04-09 09:28:44 -07:00
Mick 5cb552b1d4 refactor: multimodal data (#4754) 2025-03-31 09:57:51 -07:00
Mick 1e86457c90 model: Minicpmo (#3023) 2025-03-24 20:08:40 -07:00
Mick 11577cedb7 refactor: bug fixes and refactor for vlm (#4661) 2025-03-22 22:48:49 -07:00
Mick d373a48c98 fix: second_per_grid_ts should be used to get mrope position (#3682) 2025-03-17 18:12:38 -07:00
Mick 98be3bd306 refactor: rewrite bench-mmmu-sglang (#4458) 2025-03-17 18:11:47 -07:00
Mick 0f52fb55ec config: Update fused moe config (#4493) 2025-03-16 23:51:58 -07:00
Mick 9d02bb3e2a Urgent model support: support gemma-3-it (#4424) 2025-03-16 17:37:32 -07:00
Mick 8ec2ce0726 perf: update fused moe config (#4459) 2025-03-15 21:23:57 -07:00
Mick 035ac2ab74 ci: update transformers==4.48.3 (#4451) 2025-03-15 13:27:26 -07:00
Mick 01090e8ac3 model: Support Janus-pro (#3203) 2025-03-12 11:02:11 -07:00
Mick ff2ce0b86f refactor: move image processors to separate files (#4229) 2025-03-11 12:35:35 -07:00
Mickandzhaochenyang20 583d6af71b example: add vlm to token in & out example (#3941)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-03-04 22:18:26 -08:00
Mick 45205d88a0 bench: Add MMMU benchmark for vLM (#3562) 2025-02-22 08:10:59 -08:00
Mick 99c1b9d2ee fix: apply cache size limit of attention mask for VisionAttention (#3657) 2025-02-19 20:16:48 +08:00
Mick 424848d26f fix: remove dependency on latest transformers impl (#3635) 2025-02-19 01:14:11 +08:00
Mick bcc213df61 Model: Support Qwen 2.5 vl (#3258) 2025-02-16 00:58:53 -08:00
MickandChayenne 7711ac6ed0 doc: emphasize and notify the usage of chat_template (#3589)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
2025-02-15 00:10:32 -08:00
Mickandzhaochenyang20 ced680663c doc: Support a new vLM (#3405)
Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
2025-02-12 00:43:14 -08:00
Mick 9f635ea50d [Fix] Address remaining issues of supporting MiniCPMV (#2977) 2025-01-28 00:22:13 -08:00
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
Mick 1775b963db [Fix] fix incorrectly overwriting the port specified in ServerArgs (#2714) 2025-01-02 10:28:22 -08:00