-
Notifications
You must be signed in to change notification settings - Fork 268
Pull requests: alibaba/rtp-llm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat(sm120): enable DSv4 Flash 0731 inference support
#1350
opened Aug 28, 2026 by
MMadhatter
Collaborator
Loading…
feat(rocm): add shape-based AITER FMoE tuning
#1345
opened Aug 28, 2026 by
yzyDavid
Collaborator
Loading…
fix: improve RPC/cache-store diagnostics and xgrammar loading
#1344
opened Aug 28, 2026 by
xinfei-shi
Collaborator
Loading…
feat: qwen35 share expert and deepep combine overlap
#1343
opened Aug 28, 2026 by
HongminTan
Collaborator
Loading…
feat(trace): end-to-end OpenTelemetry request tracing
#1341
opened Aug 27, 2026 by
SAzwj
Contributor
Loading…
feat(cache): add native KVCM cache event publisher
#1340
opened Aug 27, 2026 by
putaopi7
Collaborator
Loading…
fix: optimize masked fp8 silu and deduplicate access log argument
#1336
opened Aug 26, 2026 by
siluzhou
Collaborator
Loading…
Drop deprecated DeepSeek smoke cases, fix DSv4 CP prefill + thinking_mode
#1333
opened Aug 26, 2026 by
netaddi
Collaborator
Loading…
4 of 5 tasks
feat(flexlb): support logical multi-engine workers
#1332
opened Aug 25, 2026 by
Martin7-1
Collaborator
Loading…
feat(rocm): optimize Qwen3.5 MTP latency and stability
#1326
opened Aug 24, 2026 by
loomts
Collaborator
Loading…
fix(moe): make ROCm MoE routers padding-safe and graph-capturable
#1325
opened Aug 24, 2026 by
loomts
Collaborator
Loading…
fix(ci-gate): explain fork rerun/approval denials instead of failing silently
#1324
opened Aug 23, 2026 by
LLLLKKKK
Collaborator
Loading…
2 of 5 tasks
feat(qwen35): enable PPU runtime and safe CUDA graph replay
#1321
opened Aug 19, 2026 by
Tanmo-ai
Contributor
Loading…
fix(indexer): keep the head gate off the fp32 activation expansion
#1319
opened Aug 19, 2026 by
Honglei-Qiu
Loading…
feat(quant): support compressed-tensors W8A8 INT8 checkpoints
#1317
opened Aug 19, 2026 by
Tanmo-ai
Contributor
Loading…
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.