-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Pull requests: mlc-ai/mlc-llm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat: resolve oci:// models via llmman serve
#3543
opened Aug 30, 2026 by
ericcurtin
Loading…
2 of 4 tasks
[Fix] argparse
type=bool makes --disaggregation and --stream impossible to turn off
#3541
opened Aug 28, 2026 by
Anai-Guo
Loading…
[Fix] Return 400 BadRequestError for malformed image URLs
#3539
opened Aug 23, 2026 by
SuperMarioYL
Loading…
[Fix] Isolate callback state across engine instances
#3538
opened Aug 23, 2026 by
zupengwang
Loading…
[Model] Enable support for GPT_OSS model
#3533
opened Aug 7, 2026 by
krishnaraj36
Contributor
Loading…
fix(serve): copy request.stop so get_generation_config can't mutate it (#3512)
#3531
opened Aug 2, 2026 by
Anai-Guo
Loading…
[Docs] update installation guide with dependency and library path ins…
#3527
opened Jul 23, 2026 by
farukerdem34
Loading…
[Chat] Add random-token benchmarking and token-count stats
#3521
opened Jul 22, 2026 by
dsing-qual
Loading…
[Docs] Recommend Python 3.13 for new environment setup (MacOS)
#3518
opened Jul 21, 2026 by
farukerdem34
Loading…
[LoRA] Add an end-to-end single-adapter runtime path for Qwen2
#3515
opened Jul 17, 2026 by
MagellaX
Contributor
Loading…
fix(protocol): check_function_call_usage raises raw KeyError on malformed tool_choice dict
#3514
opened Jul 15, 2026 by
chuenchen309
Loading…
[Bug] Raise an actionable error when libmlc_llm shared dependencies are missing
#3510
opened Jul 8, 2026 by
pjdurden
Loading…
[Llama] Support attention_bias and mlp_bias config flags
#3494
opened May 10, 2026 by
przemek-arch
Loading…
[CMake][Doc] Document BUILD_DUMMY_LIBTVM and source-build for compilation
#3493
opened May 3, 2026 by
nuri-yoo
Loading…
Preserve Unicode text in generated mlc-chat-config.json
#3491
opened Apr 29, 2026 by
mshr-h
Contributor
Loading…
[Embedding][Serve] Phase 4: Add first-class decoder embedding path
#3488
opened Apr 23, 2026 by
xthomaswang
Contributor
•
Draft
[Embedding][Serve] Phase 3: first-class encoder embedding path
#3481
opened Apr 13, 2026 by
xthomaswang
Contributor
•
Draft
[Feature] Add Qwen3.5 vision model support
#3474
opened Apr 2, 2026 by
gnguralnick
Contributor
Loading…
2 tasks done
Add binary group quantization and WebGPU sampler fixes for Bonsai/WebLLM
#3472
opened Apr 2, 2026 by
HMDRAMS-DEV
Loading…
Add NemotronH hybrid Mamba2-Attention model (Nemotron-3-Nano-4B)
#3464
opened Mar 27, 2026 by
OmarAzizi
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.