Skip to content

Pull requests: ModelTC/LightLLM

New pull request New
56 Open 1,074 Closed
56 Open 1,074 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Support GLM-5.2 (glm_moe_dsa, DeepSeek-V3.2-style DSA MoE)
#1370 opened Jun 25, 2026 by sufubao Collaborator Loading…
5
Make moe align fused deterministic
#1369 opened Jun 25, 2026 by hiworldwzj Collaborator Loading…
3
feat: fuse add and rmsnorm
#1368 opened Jun 24, 2026 by blueswhen Collaborator Loading…
3
feat: opt fa3 and flashinfer
#1367 opened Jun 23, 2026 by blueswhen Collaborator Loading…
3
feat(quant): support tensorwise fp8 w8a8 (--quant_type fp8w8a8-pt)
#1366 opened Jun 22, 2026 by sufubao Collaborator Loading…
2
fix(sampling_params): validate token-id input types via a shared helper
#1365 opened Jun 19, 2026 by SuperMarioYL Contributor Loading…
8
fix stream fc for qwen3_coder
#1364 opened Jun 18, 2026 by shihaobai Collaborator Loading…
4
Support default chat template kwargs
#1363 opened Jun 18, 2026 by sufubao Collaborator Loading…
2
fix(moe): avoid cross-warp stale read in ep_scatter prefix sum
#1362 opened Jun 16, 2026 by Anai-Guo Loading…
1
3
support ds4
#1355 opened Jun 15, 2026 by WANDY666 Contributor Loading…
feat: add gguf support
#1354 opened Jun 15, 2026 by zhangts20 Loading…
14
test(sampling_params): repair broken test collection and add verify() coverage
#1350 opened Jun 13, 2026 by SuperMarioYL Contributor Loading…
6
feat(qwen3_5_mtp): Qwen3.5 / Qwen3.5-MoE MTP speculative decoding
#1338 opened Jun 9, 2026 by sufubao Collaborator Loading…
3
feat: add multi-platform support with ascend and maca
#1335 opened Jun 8, 2026 by zhangts20 Loading…
8
feat: update disk cache params and benchmark_multiturn.py
#1333 opened Jun 8, 2026 by blueswhen Collaborator Loading…
3
Fa4 support
#1327 opened Jun 2, 2026 by blueswhen Collaborator Loading…
10
add in-process URL pool caching
#1325 opened Jun 1, 2026 by Owleye4 Contributor Loading…
3
update cpu cache load use async way.
#1318 opened May 25, 2026 by hiworldwzj Collaborator Loading…
3
support mtp for gemma4
#1316 opened May 22, 2026 by WANDY666 Contributor Loading…
4
fix: replace pickle deserialization with RestrictedUnpickler in PD WebSocket endpoints (CVE-2026-26220)
#1306 opened May 11, 2026 by nexadodigital Loading…
1
3
feat(RL): add RL support for verl
#1298 opened May 8, 2026 by shihaobai Collaborator Loading…
9
import flashqla to speedup gdn prefill
#1295 opened May 8, 2026 by WANDY666 Contributor Loading…
3
import flashqla and support cudagraph for gdn
#1292 opened May 6, 2026 by WANDY666 Contributor Loading…
3
Logging colorization + access middleware cleanup + windowed cache stats
#1289 opened May 6, 2026 by sufubao Collaborator Loading…
6 tasks done
9
[Feature] Add support for Neo++
#1274 opened Apr 17, 2026 by XHPlus Contributor Loading…
3
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.