 slaren
|
d232aca5a7
llama : initial ggml-backend integration (#4520)
|
2 лет назад |
 Marcus Dunn
|
31f27758fa
llama : allow getting n_batch from llama_context in c api (#4540)
|
2 лет назад |
 Finn Voorhees
|
56fa50819f
metal : fix `ggml_metal_log` vargs (#4373)
|
2 лет назад |
 Erik Garrison
|
0f630fbc92
cuda : ROCm AMD Unified Memory Architecture (UMA) handling (#4449)
|
2 лет назад |
 arlo-phoenix
|
562cf222b5
ggml-cuda: Fix HIP build by adding define for __trap (#4569)
|
2 лет назад |
 Jared Van Bortel
|
8fe03ffdda
common : remove incorrect --model-draft default (#4568)
|
2 лет назад |
 Johannes Gäßler
|
9154494808
CUDA: mul_mat_id always on GPU for batches >= 32 (#4553)
|
2 лет назад |
 Georgi Gerganov
|
c083718c89
readme : update coding guidelines
|
2 лет назад |
 howlger
|
880e352277
py : open merges file as 'utf-8' (#4566)
|
2 лет назад |
 bobqianic
|
66f35a2f48
cuda : better error message for ggml_get_rows (#4561)
|
2 лет назад |
|
slaren
|
1398823922
cuda : replace asserts in wrong architecture checks with __trap (#4556)
|
2 лет назад |
|
Johannes Gäßler
|
d3223afdad
llama : disable per-tensor info prints on model load (#4562)
|
2 лет назад |
 LoganDark
|
1d7a1912ce
Fix access violation in ggml_cuda_free_data if tensor->extra is NULL (#4554)
|
2 лет назад |
|
Johannes Gäßler
|
799fc22689
CUDA: Faster Mixtral prompt processing (#4538)
|
2 лет назад |
 Eric Sommerlade
|
328b83de23
ggml : fixed check for _MSC_VER (#4535)
|
2 лет назад |
|
arlo-phoenix
|
a7aee47b98
ggml-cuda: Fix HIP build (#4528)
|
2 лет назад |
|
Georgi Gerganov
|
0e18b2e7d0
llama.swiftui : add tinyllama 1.1B F16
|
2 лет назад |
|
Georgi Gerganov
|
6ff39b129d
llama.swiftui : add more models
|
2 лет назад |
 Ebey Abraham
|
b9e74f9bca
llama : add phi-2 + fix NeoX rope + ggml_mul_mat_set_prec (#4490)
|
2 лет назад |
 hankcs
|
3c04bf6da8
llama : fix try_override for bool_value which always return true (#4519)
|
2 лет назад |
|
Jared Van Bortel
|
2994f0c5a2
decode : fix logits_valid for legacy API (#4516)
|
2 лет назад |
|
Georgi Gerganov
|
b1306c4394
readme : update hot topics
|
2 лет назад |
|
Georgi Gerganov
|
800a489e4a
llama.swiftui : add bench functionality (#4483)
|
2 лет назад |
|
Jared Van Bortel
|
f7f468a97d
gguf-py : fail fast on nonsensical special token IDs (#4489)
|
2 лет назад |
 Matheus Gabriel Alves Silva
|
919c40660f
build : Check the ROCm installation location (#4485)
|
2 лет назад |
|
slaren
|
45668633fd
finetune : keep allocs alive until all allocations are done (#4486)
|
2 лет назад |
 olexiyb
|
0ffc92d2d2
server : disable llm logs if SERVER_VERBOSE is off (#3792)
|
2 лет назад |
 AdithyanI
|
8edd2b40fd
server : fix grammar being ignored (#4494)
|
2 лет назад |
 Alexey Parfenov
|
eb16dae7e7
server : fix possible ambiguity in content type charset (#4501)
|
2 лет назад |
 mzcu
|
62bd52b7bf
server : allow requests larger than 8K (#4500)
|
2 лет назад |
