Benson Wong 5d01670266 server : include speculative decoding stats when timings_per_token is enabled (#12603) ...

* Include speculative decoding stats when timings_per_token is true

New fields added to the `timings` object:

  - draft_n           : number of draft tokens generated
  - draft_accepted_n  : number of draft tokens accepted
  - draft_accept_ratio: ratio of accepted/generated

* Remove redundant draft_accept_ratio var

* add draft acceptance rate to server console output

2025-03-28 10:05:44 +02:00

..

batched

llama : add llama_vocab, functions -> methods, naming (#11110)

2025-01-12 11:32:42 +02:00

batched-bench

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

batched.swift

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

convert-llama2c-to-ggml

llama : add llama_vocab, functions -> methods, naming (#11110)

2025-01-12 11:32:42 +02:00

cvector-generator

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

deprecation-warning

Update deprecation-warning.cpp (#10619)

2024-12-04 23:19:20 +01:00

embedding

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

eval-callback

llama : add llama_vocab, functions -> methods, naming (#11110)

2025-01-12 11:32:42 +02:00

export-lora

common : refactor '-o' option (#12278)

2025-03-10 13:34:13 +02:00

gbnf-validator

Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars (#9639)

2025-01-30 19:13:58 +00:00

gen-docs

ggml : move AMX to the CPU backend (#10570)

2024-11-29 21:54:58 +01:00

gguf

GGUF: C++ refactor, backend support, misc fixes (#11030)

2025-01-07 18:01:58 +01:00

gguf-hash

GGUF: C++ refactor, backend support, misc fixes (#11030)

2025-01-07 18:01:58 +01:00

gguf-split

ci : use -no-cnv in gguf-split tests (#11254)

2025-01-15 18:28:35 +02:00

gritlm

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

imatrix

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

infill

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

jeopardy

…

llama-bench

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama.android

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llama.swiftui

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

llava

clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA backend (#12566)

2025-03-26 15:06:04 +01:00

lookahead

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

lookup

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

main

docs : bring llama-cli conversation/template docs up-to-date (#12426)

2025-03-17 21:14:32 +01:00

parallel

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

passkey

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

perplexity

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

quantize

ggml : portability fixes for VS 2017 (#12150)

2025-03-04 18:53:26 +02:00

quantize-stats

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

retrieval

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

rpc

rpc : update README for cache usage (#12620)

2025-03-28 09:44:13 +02:00

run

run: de-duplicate fmt and format functions and optimize (#11596)

2025-03-25 18:46:11 +01:00

save-load-state

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

server

server : include speculative decoding stats when timings_per_token is enabled (#12603)

2025-03-28 10:05:44 +02:00

simple

llama : add llama_vocab, functions -> methods, naming (#11110)

2025-01-12 11:32:42 +02:00

simple-chat

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

simple-cmake-pkg

repo : update links to new url (#11886)

2025-02-15 16:40:57 +02:00

speculative

speculative : fix seg fault in certain cases (#12454)

2025-03-18 19:35:11 +02:00

speculative-simple

llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)

2025-03-13 12:35:44 +02:00

sycl

[SYCL] Optimize mul_mat for Q4_0 on Intel GPU (#12035)

2025-02-24 22:33:23 +08:00

tokenize

llama : add llama_vocab, functions -> methods, naming (#11110)

2025-01-12 11:32:42 +02:00

tts

llama-tts : avoid crashes related to bad model file paths (#12482)

2025-03-21 11:12:45 +02:00

chat-13B.bat

…

chat-13B.sh

…

chat-persistent.sh

scripts : fix pattern and get n_tokens in one go (#10221)

2024-11-09 09:06:54 +02:00

chat-vicuna.sh

…

chat.sh

…

CMakeLists.txt

tts : add OuteTTS support (#10784)

2024-12-18 19:27:21 +02:00

convert_legacy_llama.py

metadata: Detailed Dataset Authorship Metadata (#8875)

2024-11-13 21:10:38 +11:00

json_schema_pydantic_example.py

…

json_schema_to_grammar.py

tool-call: fix Qwen 2.5 Coder support, add micro benchmarks, support trigger patterns for lazy grammars (#12034)

2025-03-05 13:05:13 +00:00

llama.vim

repo : update links to new url (#11886)

2025-02-15 16:40:57 +02:00

llm.vim

…

Miku.sh

…

pydantic_models_to_grammar_examples.py

repo : update links to new url (#11886)

2025-02-15 16:40:57 +02:00

pydantic_models_to_grammar.py

…

reason-act.sh

…

regex_to_grammar.py

…

server_embd.py

…

server-llama2-13B.sh

…

ts-type-to-grammar.sh

…