Issues
- 1
[REQUEST] Don't error when max_tokens request are too long causing Job required pages too small, just generate up to the available pages.
#262 opened by Originalimoc - 1
[BUG] OAI doc recommends parameter max_completion_tokens over max_tokens. Support aloneside with max_tokens.
#256 opened by Originalimoc - 4
[BUG] json_schema not always enforced
#258 opened by afoland - 11
[BUG] Llama 3.3 models not working
#260 opened by wypiki - 7
- 3
[BUG] EXL2 v0.2.5+ is broken with yarn RoPE.
#261 opened by Originalimoc - 6
[REQUEST] Better document rope_scaling/rope_alpha in wiki, and add config of yarn_rope_factor/yarn_rope_original_max_position_embeddings
#239 opened by Originalimoc - 7
[REQUEST] Vision Models
#235 opened by bdashore3 - 3
[REQUEST] Automatic Model Unloading while idling
#216 opened by TetrisBlack - 0
- 2
[REQUEST] Auto switch draft model on and off according to context length(prompt + completion).
#255 opened by Originalimoc - 1
- 3
[BUG] "Disabling GPU split because one GPU is in use" - then Tabby only uses 1 GPU
#250 opened by sammcj - 5
[BUG] Tool Calling not working for Llama 3.2 3B
#234 opened by raisbecka - 1
- 4
[BUG] [Dev branch] Failing to load non vision model
#248 opened by TyraVex - 4
[BUG] 2 concurrent requests make both stream.. FASTER than single stream? Exllamav2 issue or?
#247 opened by Originalimoc - 1
[BUG] max_seq_len can not be <= 2047
#240 opened by Originalimoc - 11
[BUG] The ability to ignore model field in request and just use current loaded model. (Ignore admin key checking if inline_model_loading set to false)
#236 opened by Originalimoc - 2
- 4
- 8
[REQUEST] Remove default value of draft_model_dir let it can be defined tabby_config.yml
#242 opened by Originalimoc - 2
[REQUEST] Better Infinity Embeddings support
#211 opened by arbi-dev - 0
[REQUEST] Document tabby_config.yml in wiki
#241 opened by Originalimoc - 2
[REQUEST] Nested model_name key
#231 opened by SinanAkkoyun - 1
- 1
[REQUEST(Maybe)] is yarn_rope_factor/yarn_rope_original_max_position_embeddings config passed/loaded to exllama?
#237 opened by Originalimoc - 2
[REQUEST] Vision support.
#229 opened by Ph0rk0z - 0
- 3
Exceptions when shutting down with no model loaded
#202 opened by awatuna - 3
[BUG] Inline loading doesn't respect config.yml
#226 opened by Async0x42 - 4
- 2
[REQUEST] Modify strings probability, rather than outright banning with banned_strings
#223 opened by atisharma - 2
[REQUEST] FlashAttention 1 Support.
#221 opened by Abdulhanan535 - 0
[BUG] Structured Outputs?
#219 opened by ExtinctionEvent - 9
- 7
Very Strange OOM errors across multiple GPU's. OOM's, BSOD's, extreme driver crashesh all stemming from TabbyAPI
#187 opened by SytanSD - 2
- 6
- 2
- 1
[BUG] TabbyAPI uses 100% of a CPU core after a request failed due to excessively long prompt
#203 opened by NeoChen1024 - 1
[BUG]docker cannot found cuda-toolkit
#205 opened by ultranationalism - 2
- 13
[BUG] Completitions are broken
#179 opened by TyraVex - 2
- 4
[REQUEST] Make docker build action faster
#186 opened by bdashore3 - 1
[BUG] v1/template/switch is broken
#198 opened by SecretiveShell - 2
[BUG] 'TabbyConfig' object has no attribute 'from_file'. Did you mean: '_from_file'?
#196 opened by atisharma - 1
[REQUEST] Update the docker section in the wiki
#182 opened by AmgadHasan - 9
[BUG] After updating to exllamav2-0.1.9 (from 0.1.8) cannot load Mistral Large 2 123B with a draft model
#177 opened by Lissanro