mlc-ai mlc-llm issues - Githubissues

mlc-ai / mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

https://llm.mlc.ai/docs

Apache License 2.0

17.22k stars 1.34k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[WIP][CLI] Migrate CLI to use the new Engine

#2362 tqchen closed 4 hours ago
1
[Bug] Mistral MultiRound Chat Bug

#2361 tqchen opened 4 hours ago
0
[JSONFFI] Fix JSONFFI conv template. Add unit tests

#2360 rickzx closed 9 hours ago
0
[iOS] Update MLCEngine API to latest JSON FFI convention

#2359 tqchen closed 1 day ago
0
[Bugfix] Make sequence_length dtype int64 in EngineConfig. Fix Mistral engine serving issue

#2358 rickzx closed 1 day ago
0
[Model Request] Yi-1.5

#2357 0xDEADFED5 closed 1 day ago
2
执行mlc_chat命令时，提示tvm模块找不到。

#2356 wangmiaojun opened 2 days ago
0
[Question] How do you convert .bin files to wasm. Also where are TVM_HOME and MLC_HOME located?

#2355 justrach opened 2 days ago
3
[Question] Single forward pass through ChatModule

#2354 caenopy opened 2 days ago
1
[Feature Request] Implement AttentionStore

#2353 kripper opened 3 days ago
0
[Doc] Cant install mlc

#2352 abpani opened 3 days ago
0
mlc-chat.apk initialize model failed

#2351 lengjing606 opened 3 days ago
0
[Question] mlc_llm serve fails with --speculative-mode, does it require certain hardware?

#2350 0xDEADFED5 opened 3 days ago
0
[Question] Can MLC quantize multimodal models?

#2349 LJ-Hao opened 3 days ago
0
[Model Request] Mamba

#2348 kmn1024 opened 3 days ago
0
[Serving] Add reset_engine in debug_entrypoints

#2347 yongwww closed 3 days ago
0
[Bug] Can't finish the build process on windows

#2346 jeanhubdesv opened 4 days ago
2
[Bug] set storage_type to uint8 for llama2 q4f16_1 can't generate normal OpenCL code.

#2345 sunzj closed 4 days ago
1
Add false for arg worker0_only in disco.empty

#2344 yongwww closed 4 days ago
1
Fix cublas offloading

#2343 vinx13 closed 4 days ago
0
[DebugChat] Fix DebugChat softmax function and save logits to debug folder

#2342 rickzx closed 5 days ago
0
[DebugChat] Fix DebugChat softmax function and save logits to debug folder

#2341 rickzx closed 5 days ago
0
[Bug] INVALID_BUFFER_SIZE

#2340 Vinaysukhesh98 opened 5 days ago
0
[Question] Can not get chat CLI working, throwing error after cloning model

#2339 BeytoA opened 5 days ago
4
[Question] Deployment of Pruned Models

#2338 qianjyM opened 5 days ago
0
[Serving] Add Medusa speculative decoding

#2337 vinx13 closed 5 days ago
0
[Eagle] Fix the requests for additional decode in eagle verify

#2336 vinx13 closed 6 days ago
0
[Serving][Grammar] Refactor GrammarStateMatcher and support LLaMA-3

#2335 Ubospica closed 5 days ago
0
[JSONFFIEngine] Refactor device argument and request_stream_callback argument

#2334 anibohara2000 closed 4 days ago
0
Could not find org.apache.tvm:tvm-android:0.1.0.

#2333 viaowp opened 6 days ago
0
[Question] Parallel computations using multiple streams?

#2332 taegeonum opened 6 days ago
0
[REFACTOR] Refactor JSONFFI Conv template

#2331 tqchen closed 6 days ago
0
[iOS] Make MLCEngine input to take in structured data

#2330 tqchen closed 1 week ago
1
[Serving] Refactor to consolidate new request prefill

#2329 vinx13 closed 1 week ago
0
[Bug] InternalError: Check failed: (res == VK_SUCCESS) is false: Vulkan Error, code=-4: VK_ERROR_DEVICE_LOST

#2328 aaaaaad333 opened 1 week ago
4
[DOCS] More clear android instruction

#2327 tqchen closed 1 week ago
0
[Bug] Error on running mlc_llm package (Unknown CMake command "tvm_file_glob")

#2326 NSTiwari closed 1 week ago
3
[Tracking] Create a CPU Compatible PagedKVCache

#2325 tqchen opened 1 week ago
0
[Tracking] Sentence Embedding Model

#2324 tqchen opened 1 week ago
2
[Bug] mlc_llm package failed once, and i cant run it again

#2323 CallMeTkt opened 1 week ago
1
[JSON FFI] Example Android Application using JSON FFI Engine

#2322 Kartik14 closed 1 day ago
0
[Android] Add `-j` option to cmake build

#2321 MasterJH5574 closed 1 week ago
0
[Feature Request] Medusa support

#2319 EmilioZhao opened 1 week ago
6
[DOCS] Remove mention of legacy modules

#2318 tqchen closed 1 week ago
0
libmodel_android.a error when build android sdk

#2317 lengjing606 closed 1 week ago
10
[Question] Can't get going on Mac M2 Chip

#2316 polajnta closed 1 week ago
3
Skip cublas dispatch for single batch

#2315 vinx13 closed 1 week ago
0
[Model] Removing unnecessary reshapes in get_logits

#2314 vinx13 closed 1 week ago
0
Include batch size in nvtx scope name

#2313 yongwww closed 1 week ago
0
[Serving] Log batch size in NVTX

#2312 vinx13 closed 1 week ago
0