second-state WasmEdge-WASINN-examples issues

second-state / WasmEdge-WASINN-examples

Apache License 2.0

217 stars 35 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[Example] ggml: support experimental embedding

#90 hydai closed 3 months ago
1
[Example] ggml: support top_p and presence_penalty

#89 hydai closed 3 months ago
1
[Example] ggml: merge dev to master after new release

#88 dm4 closed 3 months ago
1
Fix ngl and unwrap issue

#87 hydai closed 3 months ago
1
bug: Failed to run example in "wasmedge-ggml-llama-interative" with error "thread 'main' panicked at 'called `Result::unwrap()` on an `Err` value: BackendError(ContextFull)'"

#86 MaTwickenham closed 3 months ago
2
[Example] ggml: fix error about empty stream-stdout

#85 dm4 closed 4 months ago
2
[Example] ggml: fix typo

#84 dm4 closed 4 months ago
1
[Example] ggml: show llama.cpp version in metadata

#83 dm4 closed 4 months ago
0
[Example] ggml: refactor

#82 dm4 closed 4 months ago
1
[Example] ggml: fix the dup output when enabling stream-stdout

#81 hydai closed 4 months ago
1
[Example] ggml: add stream-stdout back

#80 hydai closed 4 months ago
1
[Example] ggml: add fini_single

#79 dm4 closed 4 months ago
1
[Example] ggml: show the number of input tokens before compute()

#78 dm4 closed 4 months ago
1
[Example] ggml: move belle-chat and codellama to llama-utils

#77 dm4 closed 4 months ago
1
Merge dev branch into master

#76 dm4 closed 4 months ago
1
[WASI-NN] Add single token inference

#75 dm4 closed 4 months ago
1
[Example] ggml: support repeat-penalty and temp

#74 dm4 closed 5 months ago
1
[Example] Add M3 Max to perf table

#73 katopz closed 5 months ago
2
[Example] Support metadata of ggml output

#72 dm4 closed 5 months ago
3
async example

#71 alanpoon closed 5 months ago
0
GGML_ASSERT: /Users/hydai/workspace/WasmEdge/plugins/wasi_nn/thirdparty/ggml/llama.cpp:5745: n_tokens <= n_batch

#70 niranjanakella closed 5 months ago
2
Unable to clear the context object knowledge

#69 niranjanakella closed 4 months ago
12
Failing to install WasmEdge through Curl "302 Moved Temporarily"

#68 niranjanakella closed 5 months ago
5
very slow and issues in ubuntu wsl with cuda

#67 eramax closed 2 months ago
9
Error Running WasmEdge with llama2 Model: GGML_ASSERT Failure

#66 xISSAx closed 4 months ago
9
OpenHermes-2.5-Mistral-7B-GPTQ always get [INST] <<SYS>>... for 1st question

#65 katopz closed 6 months ago
7
Get weird result for yarn-mistral-7b-64k.Q4_K_M.gguf

#64 katopz closed 6 months ago
1
Set metadata when building graph

#63 dm4 closed 5 months ago
4
[Example] Update performance table of M2 Max, the previous scores did…

#62 hydai closed 6 months ago
1
Memory keeps increasing for each inference

#61 katopz closed 6 months ago
7
[Example] Add RTX 4090 to perf table

#60 katopz closed 6 months ago
1
[Example] Add performance table of wasmedge-ggml-plugin

#59 hydai closed 6 months ago
1
[Example] Highlight how to use n_gpu_layers on CUDA hardware

#58 hydai closed 6 months ago
1
[0.13.5] CUDA error 222

#57 katopz closed 6 months ago
26
[Example] Update the installation guide of ggml interactive example

#56 hydai closed 6 months ago
1
Issue running on ARM architecture

#55 niranjanakella closed 6 months ago
6
[feat] New example `CodeLlama-13B-Instruct`

#54 apepkuss closed 6 months ago
3
[feat] New example `Belle-Llama2-13B-GGUF`

#53 apepkuss closed 6 months ago
3
[Example] Use new ggml backend with llama options support

#52 dm4 closed 6 months ago
12
Stuck very long and then got meaningless output when running llama2 inference

#51 darthjaja6 closed 6 months ago
5
[error] [WASI-NN] GGML backend: Error: prompt too long (570 tokens, max 508)

#50 niranjanakella closed 7 months ago
4
[Example] Add llama streaming example

#49 dm4 closed 6 months ago
2
free(): invalid pointer Aborted (core dumped) on arm64 arch linux.

#48 shahizat closed 6 months ago
9
Better error handling and more robust output handling

#47 juntao closed 7 months ago
2
Replace unwrap() with expect() and provide error messages.

#46 LiyanJin closed 3 months ago
5
[Docs] Update README of interactive example

#45 dm4 closed 7 months ago
1
[Example] increase the output size from 1000 to 4096*6

#44 hydai closed 7 months ago
1
[Example] Add initial question for interactive example

#43 dm4 closed 7 months ago
1
[Question] How can I obtain inference output as streaming tokens?

#42 katopz closed 7 months ago
2
docs: Add note for install errors and solutions

#41 katopz closed 7 months ago
4

Previous Next