tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 05:15:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : introduce bfloat16 support (#6412)

Browse Source 
* Introduce bfloat16 support

Many models on Hugging Face (e.g. Mistral, TinyLLaMA) use bfloat16 as
their canonical floating point format.

      ┌sign
      │
      │   ┌exponent
      │   │
      │   │      ┌mantissa
      │   │      │
      │┌──┴───┐┌─┴───┐
    0b0000000000000000 brain16

This encoding has the same number of exponent bits as float32. That
makes conversion relatively straightforward, even in the absence of
hardware support. For example, converting brain16 to binary32 means
simply shifting 16 bits to the left.

      ┌sign
      │
      │   ┌exponent
      │   │
      │   │      ┌mantissa
      │   │      │
      │┌──┴───┐┌─┴───────────────────┐
    0b00000000000000000000000000000000 IEEE binary32

The issue is that converting bf16 to fp16 can result in information
loss. Only 13% of bf16 numbers can be precisely represented in fp16
which in practice ends up being 99.71% of Mistral 7b v0.2's weights
however there is currently no way other than fp32 to get the others

      ┌sign
      │
      │  ┌exponent
      │  │
      │  │    ┌mantissa
      │  │    │
      │┌─┴─┐┌─┴──────┐
    0b0000000000000000 IEEE binary16

This change fixes that, by adding a bf16 data type to GGML. Support
for CPU inference has been implemented along with optimizations for
the AVX2, AVX512, and AVX512BF16 ISAs. Perplexity on Mistral 7b 0.2
improves somewhere around -0.0024 to -0.0046 compared to using fp16

* Remove GGML code that's not needed

* Minimize the GGML API surface area for BF16

* Remove bf16 luts

* Make the GGML header look nicer

* Fix documentation

* Apply ggerganov's fixes for test-backend-ops

* Add BF16 code for new ggml_validate_row_data() function
This commit is contained in:
Justine Tunney
2024-05-08 02:30:09 -04:00
committed by GitHub
parent c0e6fbf8c3
commit 3855416027
11 changed files with 1154 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
llama.cpp
View File

@ -3175,6 +3175,7 @@ struct llama_model_loader {
switch (type_max) {
case GGML_TYPE_F32: ftype = LLAMA_FTYPE_ALL_F32; break;
case GGML_TYPE_F16: ftype = LLAMA_FTYPE_MOSTLY_F16; break;
case GGML_TYPE_BF16: ftype = LLAMA_FTYPE_MOSTLY_BF16; break;
case GGML_TYPE_Q4_0: ftype = LLAMA_FTYPE_MOSTLY_Q4_0; break;
case GGML_TYPE_Q4_1: ftype = LLAMA_FTYPE_MOSTLY_Q4_1; break;
case GGML_TYPE_Q5_0: ftype = LLAMA_FTYPE_MOSTLY_Q5_0; break;
@ -3666,6 +3667,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) {
switch (ftype) {
case LLAMA_FTYPE_ALL_F32: return "all F32";
case LLAMA_FTYPE_MOSTLY_F16: return "F16";
case LLAMA_FTYPE_MOSTLY_BF16: return "BF16";
case LLAMA_FTYPE_MOSTLY_Q4_0: return "Q4_0";
case LLAMA_FTYPE_MOSTLY_Q4_1: return "Q4_1";
case LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16:
@ -6129,6 +6131,7 @@ static int llama_model_load(const std::string & fname, llama_model & model, llam
|| !(
model.ftype == LLAMA_FTYPE_ALL_F32 ||
model.ftype == LLAMA_FTYPE_MOSTLY_F16 ||
model.ftype == LLAMA_FTYPE_MOSTLY_BF16 ||
model.ftype == LLAMA_FTYPE_MOSTLY_Q4_0 ||
model.ftype == LLAMA_FTYPE_MOSTLY_Q4_1
)
@ -14158,13 +14161,16 @@ static void llama_tensor_dequantize_internal(
if (qtype.to_float == NULL) {
throw std::runtime_error(format("type %s unsupported for integer quantization: no dequantization available", ggml_type_name(tensor->type)));
}
} else if (tensor->type != GGML_TYPE_F16) {
} else if (tensor->type != GGML_TYPE_F16 &&
tensor->type != GGML_TYPE_BF16) {
throw std::runtime_error(format("cannot dequantize/convert tensor type %s", ggml_type_name(tensor->type)));
}
if (nthread < 2) {
if (tensor->type == GGML_TYPE_F16) {
ggml_fp16_to_fp32_row((ggml_fp16_t *)tensor->data, f32_output, nelements);
} else if (tensor->type == GGML_TYPE_BF16) {
ggml_bf16_to_fp32_row((ggml_bf16_t *)tensor->data, f32_output, nelements);
} else if (ggml_is_quantized(tensor->type)) {
qtype.to_float(tensor->data, f32_output, nelements);
} else {
@ -14173,7 +14179,14 @@ static void llama_tensor_dequantize_internal(
return;
}
size_t block_size = tensor->type == GGML_TYPE_F16 ? 1 : (size_t)ggml_blck_size(tensor->type);
size_t block_size;
if (tensor->type == GGML_TYPE_F16 ||
tensor->type == GGML_TYPE_BF16) {
block_size = 1;
} else {
block_size = (size_t)ggml_blck_size(tensor->type);
}
size_t block_size_bytes = ggml_type_size(tensor->type);
GGML_ASSERT(nelements % block_size == 0);
@ -14192,6 +14205,8 @@ static void llama_tensor_dequantize_internal(
auto compute = [qtype] (ggml_type typ, uint8_t * inbuf, float * outbuf, int nels) {
if (typ == GGML_TYPE_F16) {
ggml_fp16_to_fp32_row((ggml_fp16_t *)inbuf, outbuf, nels);
} else if (typ == GGML_TYPE_BF16) {
ggml_bf16_to_fp32_row((ggml_bf16_t *)inbuf, outbuf, nels);
} else {
qtype.to_float(inbuf, outbuf, nels);
}
@ -14552,6 +14567,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
case LLAMA_FTYPE_MOSTLY_Q5_1: default_type = GGML_TYPE_Q5_1; break;
case LLAMA_FTYPE_MOSTLY_Q8_0: default_type = GGML_TYPE_Q8_0; break;
case LLAMA_FTYPE_MOSTLY_F16: default_type = GGML_TYPE_F16; break;
case LLAMA_FTYPE_MOSTLY_BF16: default_type = GGML_TYPE_BF16; break;
case LLAMA_FTYPE_ALL_F32: default_type = GGML_TYPE_F32; break;
// K-quants